© 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. 132415
    Prev
    Next
    INDEX
    Explanations

    storyteller whose, sometimes repeated, for hunters

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

    RFP, Risk, cis, Weekend

    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
    ຜະລ
    0.52
    音楽
    0.51
    ᒫ
    0.51
     мыкты
    0.49
     اڈوں
    0.49
    囡
    0.49
     tubs
    0.49
    地に
    0.47
     веще
    0.47
     غوره
    0.46
    POSITIVE LOGITS
    en
    0.70
    ilm
    0.53
    -
    0.52
    רו
    0.51
    ed
    0.49
     can
    0.48
    <unused60>
    0.46
     module
    0.46
     =
    0.46
     <
    0.45
    Activations Density 0.000%

    No Known Activations