© 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. 134388
    Prev
    Next
    INDEX
    Explanations

    personalized cut-out, efficiency of, check in, specific projects

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

    survive, specialized, or contradictory evidence

    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
    边界
    0.50
    rut
    0.47
     concave
    0.44
     mechanized
    0.43
     کردیا
    0.43
    zantine
    0.43
     Θ
    0.42
     太
    0.42
     பசு
    0.42
     dome
    0.42
    POSITIVE LOGITS
    μού
    0.52
    का
    0.51
    бота
    0.51
    嘗
    0.49
     especialista
    0.47
    ოლოდ
    0.47
    Responding
    0.46
    िती
    0.46
    აპ
    0.46
    वेद
    0.45
    Activations Density 0.000%

    No Known Activations