© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24742
    Prev
    Next
    INDEX
    Explanations

    hash creation and attributes

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     блок
    0.46
    block
    0.44
     block
    0.43
     blocks
    0.40
     Block
    0.39
     бонус
    0.39
    ㅍ
    0.37
     fm
    0.37
    fpr
    0.37
    ｰ
    0.37
    POSITIVE LOGITS
     hash
    0.60
    Hash
    0.57
     @
    0.57
     Hash
    0.56
    hash
    0.56
     hasht
    0.49
    HASH
    0.49
     hashes
    0.48
     симво
    0.46
    hashes
    0.46
    Activations Density 0.003%

    No Known Activations