© 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. 86683
    Prev
    Next
    INDEX
    Explanations

    typically have, can do, is true

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

    questions and answers

    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
     வாழ்க்கை
    0.49
     isinstance
    0.45
     самих
    0.45
     каждого
    0.44
     повседнев
    0.44
     ī
    0.44
    —
    0.44
     самой
    0.43
     entries
    0.43
     или
    0.42
    POSITIVE LOGITS
     kellett
    0.48
    掛
    0.48
    }&=
    0.47
    azam
    0.45
    YZ
    0.45
    шення
    0.44
    ppes
    0.43
    ydat
    0.42
     landowner
    0.42
    Deleting
    0.41
    Activations Density 0.001%

    No Known Activations