© 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. 15579
    Prev
    Next
    INDEX
    Explanations

    legal citation or source

    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
    年から
    -0.93
    णि
    -0.90
    ppens
    -0.90
    羌
    -0.86
    arounds
    -0.85
    өздер
    -0.85
    なのだ
    -0.85
     dvě
    -0.84
    SetBool
    -0.84
    JUAN
    -0.84
    POSITIVE LOGITS
    Friday
    0.87
     findAll
    0.85
     tarafından
    0.83
     abbraccio
    0.83
    }()
    0.79
     farbe
    0.78
     llega
    0.77
     sesuai
    0.77
     dass
    0.75
    Tuesday
    0.74
    Activations Density 0.006%

    No Known Activations