© 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. 53357
    Prev
    Next
    INDEX
    Explanations

    to intentionally

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

    find the

    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
     ayrıca
    0.45
     Ayrıca
    0.44
     باستخدام
    0.43
    take
    0.43
     beschikbaar
    0.42
     您
    0.41
     محفوظ
    0.41
    sächlich
    0.41
     活动
    0.41
    ache
    0.40
    POSITIVE LOGITS
    ੜ
    0.50
    ਹ
    0.50
    س
    0.49
     gentle
    0.47
    ੱਖ
    0.47
    pèce
    0.47
    競馬
    0.46
     haze
    0.46
     peak
    0.45
     सतह
    0.45
    Activations Density 0.000%

    No Known Activations