© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 106522
    Prev
    Next
    INDEX
    Explanations

    dates and years

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

    today's date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ार्म
    0.45
    йдет
    0.45
    чения
    0.44
    堞
    0.44
    орк
    0.43
    ارم
    0.43
    זר
    0.42
    ரியில்
    0.42
    లో
    0.42
    ियंस
    0.42
    POSITIVE LOGITS
    1
    0.55
     the
    0.50
    ｎ
    0.46
     noon
    0.45
     pomeriggio
    0.44
    0.42
     de
    0.40
    gov
    0.40
     hour
    0.40
    2
    0.40
    Activations Density 0.009%

    No Known Activations