© 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. 15150
    Prev
    Next
    INDEX
    Explanations

    to cause, match, achieve, access

    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
     Avez
    -1.16
     stärker
    -1.13
     onPostExecute
    -1.12
     Poids
    -1.11
     deleteUser
    -1.02
    ⌵
    -1.02
    ніка
    -1.02
    Tapi
    -1.01
    ÜN
    -1.01
    formazioni
    -1.00
    POSITIVE LOGITS
     be
    1.24
     successful
    1.20
    才能
    1.18
     prawidł
    1.13
    H
    1.13
     successfully
    1.12
    SUCCESS
    1.09
    T
    1.05
     tohto
    1.05
     pretože
    1.05
    Activations Density 0.046%

    No Known Activations