© 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. 22-GEMMASCOPE-RES-131K
    7. 33916
    Prev
    Next
    INDEX
    Explanations

    prevent being not

    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_22/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
    眉头
    -1.30
    ὔ
    -1.26
    满脸
    -1.26
     mauva
    -1.25
     célè
    -1.25
    かもし
    -1.25
     wart
    -1.24
    拳头
    -1.24
    湳
    -1.22
    と思っている
    -1.21
    POSITIVE LOGITS
     any
    1.66
     get
    1.30
     too
    1.26
     just
    1.18
     over
    1.16
     all
    1.16
     from
    1.16
     kolejny
    1.16
     getting
    1.16
     anyone
    1.15
    Activations Density 0.036%

    No Known Activations