© 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. 156811
    Prev
    Next
    INDEX
    Explanations

    prevalence and frequency

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

    strategies, testing, effort

    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
     S
    0.58
    S
    0.58
    LA
    0.55
    NA
    0.53
    LS
    0.52
    LL
    0.51
    ;}
    0.51
    ESE
    0.51
    ASP
    0.50
    BO
    0.50
    POSITIVE LOGITS
     često
    0.48
     často
    0.47
     päät
    0.47
     communément
    0.46
     numerose
    0.45
     কিছুই
    0.45
    多く
    0.43
     palju
    0.43
    誇
    0.43
     fréquemment
    0.43
    Activations Density 0.000%

    No Known Activations