© 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. 173163
    Prev
    Next
    INDEX
    Explanations

    using only

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

    ETFs, data cataloging

    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
    ్రో
    0.50
     puriso
    0.43
     নুর
    0.43
     quelquefois
    0.42
    𒆕
    0.42
    㑔
    0.42
    ㅂ
    0.41
    лән
    0.41
    ੁਰ
    0.41
    秫
    0.41
    POSITIVE LOGITS
     Podcasts
    0.50
    anele
    0.50
     ETFs
    0.47
    scape
    0.47
     கட்டமை
    0.46
     Peloton
    0.46
     caos
    0.46
     whispers
    0.46
     podcasts
    0.45
     PDEs
    0.45
    Activations Density 0.001%

    No Known Activations