© 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. 32373
    Prev
    Next
    INDEX
    Explanations

    names and dates

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

    code comments and documentation

    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
    _
    0.37
    cue
    0.37
     abierta
    0.36
     belge
    0.36
     manifiesta
    0.36
     MNC
    0.36
     BBS
    0.36
     Zhong
    0.34
     Vás
    0.34
     autor
    0.34
    POSITIVE LOGITS
    馇
    0.44
    雱
    0.44
    হাত
    0.42
    aspis
    0.42
     Crops
    0.41
    Якщо
    0.40
     исследования
    0.40
     আশীর
    0.40
    ㄏ
    0.40
     Якщо
    0.40
    Activations Density 0.000%

    No Known Activations