© 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. 26307
    Prev
    Next
    INDEX
    Explanations

    cheese

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

    pronouns US band She opportunities

    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
    લ
    0.44
    ategoria
    0.44
    玄
    0.44
    琤
    0.44
     વિદ
    0.43
    て
    0.43
    те
    0.42
    Categories
    0.42
    And
    0.41
    ayı
    0.41
    POSITIVE LOGITS
    postal
    0.48
     postal
    0.47
     infrastrukt
    0.45
     retrieval
    0.44
     apportionment
    0.44
     adjusted
    0.44
     suggestions
    0.43
     د
    0.42
     attendees
    0.42
    公園
    0.42
    Activations Density 0.000%

    No Known Activations