© 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. 167
    Prev
    Next
    INDEX
    Explanations

    invadopodia

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

    suffix -ost, -or, -ior, -eros, -car, -ob

    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
     финансо
    0.39
     политики
    0.38
     سیاست
    0.34
     президент
    0.34
    शहर
    0.34
    🏬
    0.34
     президен
    0.34
    🚉
    0.34
     финанси
    0.33
     Businessman
    0.33
    POSITIVE LOGITS
    _
    0.42
    V
    0.41
     t
    0.40
    :
    0.40
     g
    0.39
     y
    0.38
    ↵
    0.37
     h
    0.37
    -
    0.37
     T
    0.37
    Activations Density 0.123%

    No Known Activations