© 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-65K
    7. 62344
    Prev
    Next
    INDEX
    Explanations

    comparing levels or degrees

    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
    6
    0.52
    5
    0.48
    2
    0.46
     and
    0.45
    9
    0.44
    8
    0.44
    7
    0.44
    4
    0.43
    ø
    0.42
    L
    0.42
    POSITIVE LOGITS
     فاذا
    0.46
    まったく
    0.43
    ુંદર
    0.43
    ဝ်
    0.42
     فيها
    0.41
     अमाउंट
    0.40
     downright
    0.40
    ឿង
    0.40
     완전히
    0.40
    ښ
    0.40
    Activations Density 0.041%

    No Known Activations