© 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. 10-GEMMASCOPE-RES-131K
    7. 128345
    Prev
    Next
    INDEX
    Explanations

    copyright notices, legal citation,or technical terms

    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
     our
    -1.76
     there
    -1.30
    there
    -1.20
     We
    -1.19
     "
    -1.13
     a
    -1.13
     There
    -1.12
     beträ
    -1.07
    delta
    -1.05
     their
    -1.04
    POSITIVE LOGITS
     sentral
    1.17
     montagnes
    1.16
     koste
    1.14
     seksual
    1.13
    STRUCTION
    1.11
    вом
    1.09
     journées
    1.07
     levering
    1.07
     talle
    1.04
    downtown
    1.04
    Activations Density 0.005%

    No Known Activations