© 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. 32234
    Prev
    Next
    INDEX
    Explanations

    not only is

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

    companies scaling

    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
     lätt
    0.48
    禮
    0.47
    alle
    0.46
     मनोविज्ञान
    0.46
    riebe
    0.45
    commuting
    0.45
    personality
    0.45
    ိန်
    0.45
     psychiatrists
    0.45
     kiệm
    0.45
    POSITIVE LOGITS
    .),
    0.46
    )')
    0.46
    <0x80>
    0.45
     Connolly
    0.44
    )".
    0.44
    .):
    0.44
    )`,
    0.43
     contention
    0.43
    充
    0.43
     boasted
    0.42
    Activations Density 0.000%

    No Known Activations