© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208689
    Prev
    Next
    INDEX
    Explanations

    instructions in text

    np_acts-logits-general · gemini-2.5-flash-lite

    tactical factor battles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::::
    0.49
    하였
    0.47
    睺
    0.45
     Meg
    0.44
    hatta
    0.44
    StatusCode
    0.44
    тор
    0.44
    з
    0.43
     অজ
    0.43
    JA
    0.43
    POSITIVE LOGITS
     closets
    0.52
    ennies
    0.51
     hallways
    0.48
     homeowner
    0.48
     storylines
    0.47
     instructions
    0.46
     чемпион
    0.46
     lineages
    0.46
     instructs
    0.45
    ቹን
    0.44
    Activations Density 0.002%

    No Known Activations