© 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. 135640
    Prev
    Next
    INDEX
    Explanations

    building with LEGOs

    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
     Cid
    0.49
    নাত
    0.48
    nSamples
    0.46
     AppComponent
    0.46
     Felder
    0.45
     slto
    0.45
     ~\
    0.45
    <0x98>
    0.44
    樂
    0.44
    ಸ್ಯ
    0.44
    POSITIVE LOGITS
     (
    0.53
     level
    0.47
    de
    0.46
     to
    0.45
    ga
    0.44
    g
    0.41
     de
    0.41
     –
    0.40
     ذر
    0.40
     parte
    0.40
    Activations Density 0.000%

    No Known Activations