© 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. 40-GEMMASCOPE-2-RES-262K
    7. 26584
    Prev
    Next
    INDEX
    Explanations

    performs an action

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.45
     колдон
    0.44
     Tard
    0.43
    lač
    0.43
     девя
    0.42
     التاس
    0.42
     κο
    0.42
     plă
    0.41
    九
    0.41
     Pop
    0.40
    POSITIVE LOGITS
    quoted
    0.38
    infer
    0.37
     spoken
    0.36
    Ceylon
    0.35
    ሳት
    0.35
    Every
    0.35
     Persia
    0.35
    elling
    0.35
    ྒ
    0.35
     locates
    0.34
    Activations Density 0.000%

    No Known Activations