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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8603
    Prev
    Next
    INDEX
    Explanations

    He verb action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    r
    0.89
    nya
    0.79
    র
    0.78
     abr
    0.77
    quela
    0.77
     misalnya
    0.75
    на
    0.74
    િયા
    0.73
    quele
    0.73
    еты
    0.73
    POSITIVE LOGITS
     fleste
    0.78
    में
    0.76
     أ
    0.72
    
    0.71
     ২২
    0.71
    बीयत
    0.71
     끝
    0.71
     트
    0.71
    asting
    0.70
    Ⅶ
    0.69
    Activations Density 0.922%

    No Known Activations