© 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. 128936
    Prev
    Next
    INDEX
    Explanations

    objective value, score, or accuracy

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Ufer
    -0.92
    unteers
    -0.92
     contará
    -0.89
    culas
    -0.88
    前言
    -0.86
     reembolso
    -0.86
    mensa
    -0.85
    ใด
    -0.85
    omens
    -0.84
    kyat
    -0.84
    POSITIVE LOGITS
    Initializing
    0.94
    可怜
    0.88
     peup
    0.82
    шите
    0.81
     profiter
    0.79
    }]
    0.79
     борьбе
    0.78
    ぽん
    0.78
     Bearbeit
    0.77
    别人
    0.77
    Activations Density 0.008%

    No Known Activations