© 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. 24400
    Prev
    Next
    INDEX
    Explanations

    school names and types

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

    concepts, lists, or examples

    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
    Helix
    0.52
    ז
    0.52
    Пре
    0.48
     Contacts
    0.46
    फ
    0.44
     Encryption
    0.44
    С
    0.43
    تر
    0.43
    इन
    0.43
     Incre
    0.43
    POSITIVE LOGITS
     tutaj
    0.57
    divider
    0.53
     aici
    0.52
     burada
    0.52
    udson
    0.51
    ohnt
    0.50
    learner
    0.49
     senare
    0.49
    authorised
    0.48
     Pollard
    0.47
    Activations Density 0.000%

    No Known Activations