© 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. 136368
    Prev
    Next
    INDEX
    Explanations

    defining states and actions

    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
     бушлай
    0.55
    hôtel
    0.46
    𝒐
    0.45
     уйнау
    0.45
    𝘪
    0.44
    inerja
    0.44
     ServicePolicy
    0.43
    irlos
    0.43
    hilt
    0.42
    ahaman
    0.42
    POSITIVE LOGITS
     እንቅ
    0.44
     grievous
    0.44
     cries
    0.44
     mo
    0.44
    (__
    0.44
     abduction
    0.43
     দুঃ
    0.43
    懼
    0.43
     skul
    0.43
     instability
    0.42
    Activations Density 0.002%

    No Known Activations