© 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. 15676
    Prev
    Next
    INDEX
    Explanations

    descriptive classifiers

    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
     acidente
    -1.16
     But
    -1.16
     hvilke
    -1.12
     restricciones
    -1.10
     sought
    -1.06
     amassed
    -1.04
     domínio
    -1.00
     мужская
    -0.98
    日在
    -0.98
     inimigo
    -0.96
    POSITIVE LOGITS
     approach
    1.41
    izmus
    1.26
     nature
    1.23
    şit
    1.21
     دیگر
    1.20
    🦹
    1.15
     benzin
    1.10
    ادامه
    1.09
    توضی
    1.07
    ēju
    1.07
    Activations Density 0.128%

    No Known Activations