© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15830
    Prev
    Next
    INDEX
    Explanations

    separators and subsequent descriptors

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

    mathematical symbols and operators

    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
    ,
    0.41
    덟
    0.39
    .'),
    0.39
     എന്നാണ്
    0.38
    zelfde
    0.38
    ၄
    0.38
     sensiblement
    0.37
     metų
    0.37
     maupun
    0.36
     Saltar
    0.36
    POSITIVE LOGITS
    with
    0.40
    rogens
    0.37
    мана
    0.36
    تر
    0.35
    眼的
    0.34
    ولات
    0.34
     विजेता
    0.33
    дон
    0.33
    ":"
    0.33
    मीन
    0.33
    Activations Density 0.088%

    No Known Activations