© 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. 33441
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    づけ
    -1.32
    に行って
    -1.23
     it
    -1.10
     or
    -1.09
     tirada
    -1.06
    に挑戦
    -1.02
    にしました
    -1.02
     risico
    -1.02
    berte
    -0.99
     delicada
    -0.98
    POSITIVE LOGITS
    などが
    1.52
    などを
    1.32
    again
    1.23
    それも
    1.18
     again
    1.17
    などの
    1.12
    JOSE
    1.11
    そういった
    1.09
    と思ったら
    1.07
     abusi
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.