© 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. 95104
    Prev
    Next
    INDEX
    Explanations

    words in different languages

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

    Fedora, Grav, server, restarts

    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
     Constitu
    0.44
     tendría
    0.44
    ↵
    0.43
    ly
    0.43
    Enc
    0.42
    的海
    0.42
     conformado
    0.42
     concurs
    0.42
     Compet
    0.41
    al
    0.40
    POSITIVE LOGITS
    Mobs
    0.57
     ਆਪਣੇ
    0.51
    点の
    0.51
     effluents
    0.51
    ὢ
    0.49
    kadang
    0.48
     lakhs
    0.48
    点は
    0.48
    過ご
    0.48
     बिंदुओं
    0.47
    Activations Density 0.000%

    No Known Activations