© 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. 164500
    Prev
    Next
    INDEX
    Explanations

    locations followed by prepositions or nouns

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

    pro version, north shore, mature coconuts, casual wear

    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
     kapcsolat
    0.44
    lope
    0.43
     ще
    0.41
    <0x9F>
    0.41
    動力
    0.41
    bo
    0.41
    UR
    0.41
    JP
    0.40
    UL
    0.40
    視
    0.40
    POSITIVE LOGITS
     फ़रवरी
    0.51
     تمامی
    0.49
     اهمیت
    0.48
     fórmulas
    0.46
    庆祝
    0.46
    .[[
    0.45
     réalisées
    0.43
     formulations
    0.42
     Scatter
    0.42
     Formulas
    0.42
    Activations Density 0.001%

    No Known Activations