© 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. 52907
    Prev
    Next
    INDEX
    Explanations

    help Palestinian could good lod

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

    compound nouns or descriptive phrases

    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
     supplementation
    0.40
    物を
    0.39
    enterprise
    0.39
     enterprise
    0.39
     sinister
    0.38
    物が
    0.37
    윽
    0.37
    运算符
    0.37
    _
    0.37
    infix
    0.36
    POSITIVE LOGITS
     enseignants
    0.45
    帮助
    0.44
     தேர்வு
    0.43
     écriv
    0.41
     égal
    0.41
     aé
    0.41
    ساعدة
    0.41
     êtres
    0.41
    ෂ
    0.41
    无人
    0.40
    Activations Density 0.001%

    No Known Activations