© 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. 142023
    Prev
    Next
    INDEX
    Explanations

    spare parts earn money

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

    feature extraction and learning

    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
    эй
    0.48
    𝐽
    0.48
     它
    0.48
    IDOS
    0.47
    FCC
    0.46
    নির্ম
    0.46
     penta
    0.46
    Wei
    0.46
    エ
    0.45
    Ao
    0.44
    POSITIVE LOGITS
     verhindert
    0.45
    !
    0.44
     demoral
    0.43
     females
    0.43
    zees
    0.41
     beginnen
    0.41
     Midwestern
    0.41
     وج
    0.40
    ແລະ
    0.40
     وإ
    0.40
    Activations Density 0.000%

    No Known Activations