© 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. 19596
    Prev
    Next
    INDEX
    Explanations

    action or consequence

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

    elasticity and feasibility calculations

    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
    ates
    0.49
     ਰਾ
    0.49
    ardin
    0.48
    orra
    0.47
     फेव
    0.46
    /
    0.45
    helia
    0.45
    クタ
    0.43
     খবর
    0.43
     familiare
    0.43
    POSITIVE LOGITS
    ళ్
    0.46
    dır
    0.45
     playable
    0.45
     be
    0.44
     bluff
    0.43
    щается
    0.43
    izontally
    0.42
    Գ
    0.42
    ifikat
    0.41
    डाय
    0.41
    Activations Density 0.000%

    No Known Activations