© 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. 27196
    Prev
    Next
    INDEX
    Explanations

    wedding and online degrees

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

    Magic Circle, Somali, program, effect

    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
     boreal
    0.49
     naphthalene
    0.45
     stratum
    0.44
     excretion
    0.43
     pathogen
    0.43
     строку
    0.43
    ثله
    0.43
    燧
    0.43
     epiphany
    0.42
     sulph
    0.41
    POSITIVE LOGITS
     മെ
    0.45
     Cub
    0.44
    offe
    0.43
    ôn
    0.42
     Phill
    0.42
     Oscar
    0.42
    urals
    0.42
    ying
    0.41
    iffer
    0.41
     Sports
    0.41
    Activations Density 0.000%

    No Known Activations