© 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. 57509
    Prev
    Next
    INDEX
    Explanations

    gameplay and player activities

    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
    ču
    -1.11
    -0.97
    VStack
    -0.93
    yaszt
    -0.90
     öf
    -0.89
    сион
    -0.87
    简约
    -0.85
    zuje
    -0.84
    neurs
    -0.84
    eltjes
    -0.84
    POSITIVE LOGITS
    polish
    1.12
     our
    1.10
     jugador
    1.05
    μαστε
    1.01
     لاعب
    0.96
     VFX
    0.96
     player
    0.95
     dramatist
    0.93
     Metacritic
    0.93
     we
    0.92
    Activations Density 0.032%

    No Known Activations