© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    more than likely

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

    "very" followed by descriptive word

    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
    ۔
    0.36
    IONS
    0.35
    ().
    0.35
     isotherms
    0.34
    는
    0.34
    ->
    0.33
    ENSE
    0.33
     embeddings
    0.32
    ），
    0.32
     isomorphisms
    0.32
    POSITIVE LOGITS
    на
    0.35
     fortunate
    0.35
     complacent
    0.33
    си
    0.33
    ד
    0.32
    注重
    0.31
     pricey
    0.31
    кратно
    0.31
    t
    0.30
     lucrative
    0.30
    Activations Density 0.731%

    No Known Activations