© 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. 18085
    Prev
    Next
    INDEX
    Explanations

    chestnut pond

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

    Twitter conversations & teams

    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
     excised
    0.46
     Nieu
    0.43
     willfully
    0.42
     referred
    0.41
    清
    0.41
    suites
    0.40
    <0x9C>
    0.40
     encouraged
    0.40
     organismo
    0.40
     phoned
    0.39
    POSITIVE LOGITS
    ApiCalls
    0.48
     स्वर
    0.46
    𝐺
    0.43
    ilingual
    0.43
    ന്വേഷ
    0.43
    ത്തര
    0.42
    cepat
    0.42
    Ｃ
    0.41
     กลุ่ม
    0.41
     चलेंगे
    0.41
    Activations Density 0.000%

    No Known Activations