© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21061
    Prev
    Next
    INDEX
    Explanations

    candidates of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    0.58
    (
    0.56
    ве
    0.49
    Servers
    0.49
    he
    0.48
    back
    0.48
    able
    0.47
    (__
    0.46
    C
    0.44
    honest
    0.44
    POSITIVE LOGITS
     naturelles
    0.53
     εικό
    0.52
     उसकी
    0.52
    𒋀
    0.52
     terminó
    0.51
     राइट
    0.50
     empezó
    0.50
     planificación
    0.50
     नर्मदा
    0.50
     প্রণ
    0.50
    Activations Density 0.001%

    No Known Activations