© 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. 22144
    Prev
    Next
    INDEX
    Explanations

    Target audience members

    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
    Clone
    0.49
    G
    0.49
    BF
    0.44
    clone
    0.40
    сли
    0.40
     clone
    0.40
    pm
    0.39
    ::
    0.38
     に
    0.38
    С
    0.38
    POSITIVE LOGITS
     UIColor
    0.45
    酺
    0.44
    蔷
    0.40
    ድረግ
    0.40
    唿
    0.40
     সম্ভব
    0.40
     دوبارہ
    0.39
     Chief
    0.39
     Debbie
    0.39
    दायी
    0.38
    Activations Density 0.001%

    No Known Activations