© 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. 16175
    Prev
    Next
    INDEX
    Explanations

    explaining research findings

    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
     I
    -1.57
     itself
    -1.40
     its
    -1.35
     me
    -1.31
     Schwier
    -1.27
     которое
    -1.20
     मुझे
    -1.18
     παιδιά
    -1.17
    junto
    -1.17
     verbringen
    -1.16
    POSITIVE LOGITS
     ourselves
    2.14
     our
    1.53
     the
    1.46
    Our
    1.37
     in
    1.34
     We
    1.21
     czerwca
    1.16
     lutego
    1.08
    /**
    1.05
     épices
    1.05
    Activations Density 0.126%

    No Known Activations