© 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. 31130
    Prev
    Next
    INDEX
    Explanations

    overall goal or rating

    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
    明显的
    -1.19
    denn
    -1.16
    ꯵
    -1.13
    guantes
    -1.13
    终究
    -1.11
     końcu
    -1.09
     vuestro
    -1.05
     lã
    -1.05
    涠
    -1.04
    ⬈
    -1.04
    POSITIVE LOGITS
     assessment
    1.34
     winner
    1.31
     experience
    1.31
     picture
    1.25
     however
    1.20
    就
    1.19
    F
    1.19
     effect
    1.18
     it
    1.16
    package
    1.16
    Activations Density 0.016%

    No Known Activations