© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112375
    Prev
    Next
    INDEX
    Explanations

    achieving outcomes through action

    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_10/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
    by
    -1.48
     of
    -1.42
    It
    -1.33
    通常
    -1.29
     podob
    -1.25
     新作
    -1.23
     zoals
    -1.22
     vorhandenen
    -1.21
     betreffenden
    -1.20
    Similarly
    -1.20
    POSITIVE LOGITS
     and
    2.09
     now
    1.78
     not
    1.66
     sometimes
    1.57
    uttgart
    1.50
     zařízení
    1.45
    泚
    1.45
     akkor
    1.41
     what
    1.41
     část
    1.41
    Activations Density 0.146%

    No Known Activations