© 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. 69778
    Prev
    Next
    INDEX
    Explanations

    security and conditions

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

    explaining perspective or advice

    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
     dispuestos
    0.47
    (`./
    0.45
    もう
    0.45
     уж
    0.45
    より
    0.45
    ходи
    0.43
    もし
    0.42
    それぞれの
    0.42
    大陸
    0.42
     parro
    0.41
    POSITIVE LOGITS
    ان
    0.52
     Concerns
    0.51
     أس
    0.50
    Proposal
    0.48
     Correction
    0.47
    Correction
    0.47
    芓
    0.47
    Arquivo
    0.46
    ار
    0.46
     Proposal
    0.45
    Activations Density 0.001%

    No Known Activations