© 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. 34-GEMMASCOPE-RES-131K
    7. 77658
    Prev
    Next
    INDEX
    Explanations

    even the most

    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_34/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
     either
    -2.09
    either
    -1.58
    ITHER
    -1.57
    とにかく
    -1.55
     both
    -1.54
    Either
    -1.53
    both
    -1.45
     any
    -1.44
     anything
    -1.35
     zarówno
    -1.34
    POSITIVE LOGITS
     самых
    1.63
     seemingly
    1.34
     smallest
    1.34
     σήμερα
    1.31
     aparentemente
    1.28
     самая
    1.20
     самые
    1.19
    Those
    1.19
     najbardziej
    1.19
     nachdem
    1.16
    Activations Density 0.051%

    No Known Activations