© 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. 22033
    Prev
    Next
    INDEX
    Explanations

    honey, many countries, moment of, clean when

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

    tendency towards

    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
    و
    0.64
    夼
    0.52
    I
    0.48
    Battery
    0.48
    бата
    0.47
    atori
    0.46
    ެއް
    0.46
     бата
    0.46
    اتی
    0.45
     پیش
    0.45
    POSITIVE LOGITS
     alphas
    0.47
     assemblages
    0.47
    ten
    0.46
     individualism
    0.44
    Ρ
    0.44
     traumas
    0.43
     mRNAs
    0.42
     peculiarities
    0.41
     benzodiazep
    0.41
     essences
    0.41
    Activations Density 0.000%

    No Known Activations