© 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. 64052
    Prev
    Next
    INDEX
    Explanations

    update, biology, botany, boiling

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

    causing seriousfor preciseReview contextinvolve discussingconcerning sensitiveviolate expectationsfine details

    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
     is
    0.50
     {},
    0.50
     неко
    0.45
     বহুম
    0.43
    mailbox
    0.43
     displayName
    0.42
     benefits
    0.42
     caseworker
    0.42
     pictureBox
    0.42
     получение
    0.42
    POSITIVE LOGITS
    狍
    0.49
    㵴
    0.47
    뚫
    0.46
    ਔ
    0.46
     nematodes
    0.45
    äub
    0.44
     ongeveer
    0.44
    jez
    0.43
     dotyczą
    0.42
     dirigés
    0.42
    Activations Density 0.000%

    No Known Activations