© 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. 82126
    Prev
    Next
    INDEX
    Explanations

    technical leader recipes fruit

    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
    гне
    0.52
     Ouv
    0.45
    균
    0.45
    只有
    0.42
     Nunca
    0.42
    暗
    0.41
    很容易
    0.41
    白
    0.41
     वज
    0.40
    你
    0.39
    POSITIVE LOGITS
    ENCI
    0.53
     baya
    0.50
    seventh
    0.48
    stad
    0.46
    ss
    0.45
     पका
    0.44
    aldi
    0.44
    to
    0.43
    ਾਮ
    0.43
    AES
    0.43
    Activations Density 0.000%

    No Known Activations