© 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. 200221
    Prev
    Next
    INDEX
    Explanations

    common words and names

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

    recognizes otherness

    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
    ۇ
    0.49
     unconsciously
    0.49
    ﻑ
    0.47
     unknowingly
    0.43
     supposedly
    0.43
     chronically
    0.42
    hops
    0.42
     I
    0.42
     unwittingly
    0.42
     easily
    0.42
    POSITIVE LOGITS
     തിരിച്ച
    0.52
     décider
    0.47
    ovington
    0.46
     раху
    0.46
    儘
    0.45
    alade
    0.44
    រ
    0.43
    emeni
    0.43
     zez
    0.43
    ឃើញ
    0.43
    Activations Density 0.002%

    No Known Activations