© 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. 21272
    Prev
    Next
    INDEX
    Explanations

    making mistakes

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

    income, tree, schema, year, accounting, obligation, cavity, warehouse

    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
     Präsident
    0.49
    级别的
    0.45
     Maximal
    0.45
     অশ্লীল
    0.45
     possíveis
    0.45
     Motivational
    0.44
     Etihad
    0.44
    颦
    0.44
     ponencia
    0.43
     unapolog
    0.43
    POSITIVE LOGITS
    .<
    0.53
     इनकम
    0.46
     children
    0.46
    .\\
    0.46
     agricultura
    0.45
    kala
    0.44
    Into
    0.43
     forestry
    0.43
    consumers
    0.43
    became
    0.42
    Activations Density 0.000%

    No Known Activations