© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52651
    Prev
    Next
    INDEX
    Explanations

    Requirement, children, games

    np_acts-logits-general · gemini-2.5-flash-lite

    LitRPG genre indicator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     January
    0.62
    ↵
    0.59
     State
    0.52
     Boston
    0.51
     URI
    0.51
     Portland
    0.50
     "
    0.49
     In
    0.49
     Universal
    0.49
     ATM
    0.49
    POSITIVE LOGITS
     御
    0.60
     alteraciones
    0.52
    晎
    0.52
    agés
    0.52
    góc
    0.51
     ఉందని
    0.50
     ながら
    0.50
    ᚋ
    0.50
    pieza
    0.50
     bicovariant
    0.50
    Activations Density 0.000%

    No Known Activations