© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 243322
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and specific nouns

    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
    các
    0.53
    ặ
    0.52
     อย่าง
    0.51
     warmly
    0.50
     Nası
    0.49
     polygons
    0.49
     Respir
    0.49
    萫
    0.48
     fémin
    0.48
    ных
    0.47
    POSITIVE LOGITS
     LocalDate
    0.45
    Shell
    0.45
    bells
    0.44
    wings
    0.44
    ringing
    0.44
    helicopter
    0.43
    CodeAttribute
    0.43
    łka
    0.42
    晚
    0.42
    renewal
    0.42
    Activations Density 0.000%

    No Known Activations