© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12855
    Prev
    Next
    INDEX
    Explanations

    strategy guide

    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
    nossa
    -1.52
    klart
    -1.45
     our
    -1.44
    ₑ
    -1.35
    hadapi
    -1.35
    ✏️
    -1.32
     Gelen
    -1.31
     komment
    -1.30
    IBRATION
    -1.27
     fön
    -1.25
    POSITIVE LOGITS
     to
    1.34
     play
    1.27
     einiger
    1.23
     strategy
    1.18
     near
    1.16
    targeting
    1.13
     STRATEG
    1.10
     you
    1.06
     音乐
    1.06
     stay
    1.03
    Activations Density 0.010%

    No Known Activations