© 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. 10-GEMMASCOPE-RES-131K
    7. 9576
    Prev
    Next
    INDEX
    Explanations

    private communication

    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
     on
    -1.42
     of
    -1.33
     Also
    -1.31
     During
    -1.27
     Some
    -1.24
     were
    -1.23
     How
    -1.20
     —
    -1.18
     it
    -1.17
    もある
    -1.16
    POSITIVE LOGITS
     secr
    1.50
     préparer
    1.48
    reys
    1.38
     elegancia
    1.31
    docks
    1.30
    promise
    1.27
    lows
    1.27
    Ŷ
    1.26
    versus
    1.26
    lle
    1.25
    Activations Density 0.015%

    No Known Activations