© 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. 196198
    Prev
    Next
    INDEX
    Explanations

    business and technical terms

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

    hypotheses, like, typically

    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
     Rossi
    0.49
    毽
    0.47
     क्लब
    0.46
     rzecz
    0.46
    ász
    0.45
     cordial
    0.45
     Bastian
    0.45
     Klub
    0.44
     Unterstützung
    0.44
    mény
    0.43
    POSITIVE LOGITS
    s
    0.55
     defects
    0.47
    номо
    0.47
    alve
    0.46
    მ
    0.46
    residual
    0.45
     EBIT
    0.44
     copying
    0.43
    onen
    0.43
    atr
    0.43
    Activations Density 0.000%

    No Known Activations