© 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. 135433
    Prev
    Next
    INDEX
    Explanations

    instructions and actionable advice

    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
     keyDown
    0.54
     стаўкі
    0.47
     headaches
    0.47
     সা
    0.45
     chases
    0.45
     মুখো
    0.44
    轪
    0.44
    handleChange
    0.44
     예
    0.44
     гиб
    0.43
    POSITIVE LOGITS
    ap
    0.61
    en
    0.52
    et
    0.51
    un
    0.50
    ain
    0.50
     historical
    0.50
    el
    0.49
    om
    0.47
     marvelous
    0.47
     ancestral
    0.47
    Activations Density 0.005%

    No Known Activations