© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30598
    Prev
    Next
    INDEX
    Explanations

    code, licenses, and copyright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setText
    -0.83
    𝕮
    -0.71
    Bru
    -0.68
    crate
    -0.67
     Bru
    -0.67
    Jo
    -0.66
    rid
    -0.66
    Mah
    -0.65
    Jesus
    -0.64
    ขึ้น
    -0.64
    POSITIVE LOGITS
    Flashcards
    0.79
    Repost
    0.75
    longest
    0.75
     Thrust
    0.74
    acij
    0.74
    Academics
    0.73
    conc
    0.73
    鹄
    0.72
    Фак
    0.71
    Dich
    0.71
    Activations Density 0.052%

    No Known Activations