© 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. 60036
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    rely, circulated, rise, often

    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
     electoral
    0.48
     ۱۹
    0.47
     |_
    0.47
     bebida
    0.46
    tabular
    0.45
    笑着
    0.45
     soundtracks
    0.44
     apuesta
    0.44
     မ
    0.44
    )$,
    0.43
    POSITIVE LOGITS
    rant
    0.46
    bere
    0.44
    ყენ
    0.43
    natives
    0.43
    அது
    0.43
    mity
    0.43
    CSF
    0.43
    nA
    0.43
    steuerung
    0.42
     COP
    0.42
    Activations Density 0.000%

    No Known Activations