© 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. 202879
    Prev
    Next
    INDEX
    Explanations

    mobile app, head of

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

    uniform cookies

    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
    நாட்டு
    0.54
    জাতি
    0.51
     ভাষায়
    0.50
    ται
    0.49
     Gaia
    0.47
    אות
    0.47
     *)$
    0.47
    Gaia
    0.46
    Languages
    0.46
    эле
    0.46
    POSITIVE LOGITS
    sa
    0.48
    ôle
    0.47
    saf
    0.43
    åd
    0.42
    après
    0.42
    žem
    0.42
    äl
    0.41
    ingen
    0.41
    ă
    0.41
     snar
    0.40
    Activations Density 0.002%

    No Known Activations