© 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. 30869
    Prev
    Next
    INDEX
    Explanations

    your domain or role

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

    your + possession/goal/solution

    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
    全体
    0.45
    ქვენ
    0.44
    いま
    0.44
    acola
    0.44
    ジム
    0.44
    acterium
    0.44
    শিশ
    0.43
    陬
    0.43
    iyam
    0.43
    ijima
    0.42
    POSITIVE LOGITS
     onc
    0.42
     enter
    0.41
     analogs
    0.40
     inn
    0.40
     तैयारी
    0.40
     preparations
    0.39
     alone
    0.39
     spatial
    0.39
     presents
    0.39
     closest
    0.39
    Activations Density 0.000%

    No Known Activations