© 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. 203324
    Prev
    Next
    INDEX
    Explanations

    following phrases with common words

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

    actions or the roles behind them

    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
    μένο
    0.53
    μοί
    0.50
     Зем
    0.48
    寘
    0.48
     Aoki
    0.46
    મારા
    0.46
     réduit
    0.46
    ovať
    0.46
    ού
    0.44
     didnt
    0.44
    POSITIVE LOGITS
     childcare
    0.46
     use
    0.43
     Boundary
    0.42
    EARCH
    0.41
     inad
    0.41
    BURTS
    0.40
     industrious
    0.40
    *\
    0.40
     holiness
    0.40
    gul
    0.39
    Activations Density 0.000%

    No Known Activations