© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26586
    Prev
    Next
    INDEX
    Explanations

    public, private, protected keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to protected‐visibility constructor declarations (i.e. “protected” followed by a class name and its () constructor signature).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     («
    -0.93
     informaron
    -0.92
    }:
    -0.91
    ﾚ
    -0.85
    رژی
    -0.85
     conclure
    -0.85
    кульп
    -0.84
    onavirus
    -0.84
     lies
    -0.83
     descripción
    -0.82
    POSITIVE LOGITS
     pourquoi
    0.94
    дові
    0.94
    հ
    0.91
     успешно
    0.88
     and
    0.86
    ございました
    0.86
    ystis
    0.85
    rieben
    0.82
    never
    0.82
    学部
    0.82
    Activations Density 0.008%

    No Known Activations