© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3867
    Prev
    Next
    INDEX
    Explanations

    Y followed by various

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    Sp
    3.10
    @@]
    2.99
    Signin
    2.92
    ὅ
    2.90
    breakpoints
    2.87
    Ass
    2.87
    INS
    2.85
    WebV
    2.82
    Ἠ
    2.80
    Gson
    2.79
    POSITIVE LOGITS
    ോഗ്യ
    3.49
    <bos>
    3.32
    ান্ত্রিক
    3.11
    ন্ত্রণ
    3.11
    vonne
    2.90
    থেষ্ট
    2.88
    ী
    2.74
    莠
    2.70
    alnız
    2.70
    ंत्रिकी
    2.63
    Activations Density 0.256%

    No Known Activations