© 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. 31-GEMMASCOPE-2-RES-262K
    7. 80335
    Prev
    Next
    INDEX
    Explanations

    English translation of instructions

    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
    Negative Logits
    ної
    0.51
    મુ
    0.48
    ぐらい
    0.47
    ᆹ
    0.47
     drugo
    0.47
    dv
    0.46
    り
    0.45
     exclusions
    0.45
    ون
    0.45
    它
    0.44
    POSITIVE LOGITS
     Init
    0.46
     optimized
    0.44
     Ded
    0.43
     Coral
    0.42
    nonatomic
    0.41
     examined
    0.40
     Đài
    0.40
     Sus
    0.40
     Forbes
    0.40
     Initiate
    0.40
    Activations Density 0.004%

    No Known Activations