© 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. 168295
    Prev
    Next
    INDEX
    Explanations

    pathfinding and cost calculation

    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
     RULES
    0.42
    issense
    0.42
     chapitre
    0.41
    /[\
    0.40
    maskedTextBox
    0.40
     डॉक्यूमेंट्री
    0.40
     intramolecular
    0.39
    ",&
    0.38
    RULES
    0.38
    ᄊ
    0.38
    POSITIVE LOGITS
     heuristic
    0.59
    heuristic
    0.55
     open
    0.54
     cost
    0.52
     costs
    0.51
    启发
    0.51
     Open
    0.50
     estimate
    0.48
     Opens
    0.48
     heuristics
    0.48
    Activations Density 0.017%

    No Known Activations