© 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. 53220
    Prev
    Next
    INDEX
    Explanations

    private open

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

    Google DeepMind

    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
     from
    0.46
     with
    0.44
     duplex
    0.44
     (
    0.43
     options
    0.42
     interruptions
    0.42
     values
    0.41
    sts
    0.41
     mortality
    0.41
    ↵
    0.40
    POSITIVE LOGITS
    बंधनाच्या
    0.49
     наши
    0.49
    สนามกีฬา
    0.47
    궂
    0.46
     núi
    0.46
    ท่องเที่ยว
    0.46
    难道
    0.45
    रासायनिक
    0.45
    деа
    0.44
    uvre
    0.44
    Activations Density 0.000%

    No Known Activations