© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8964
    Prev
    Next
    INDEX
    Explanations

    return or again

    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_65k_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
     disclosure
    0.40
     %>
    0.39
    outputs
    0.38
    disclosure
    0.38
     subtracting
    0.36
     departs
    0.36
    pbs
    0.36
     Related
    0.35
     DISABLE
    0.35
     localVarAccept
    0.35
    POSITIVE LOGITS
     kembali
    1.84
    に戻
    1.68
     Kembali
    1.62
     తిరిగి
    1.60
     다시
    1.59
    戻
    1.57
     دوبارہ
    1.53
     tekrar
    1.52
    重新
    1.48
     மீண்டும்
    1.47
    Activations Density 0.232%

    No Known Activations