© 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. 188401
    Prev
    Next
    INDEX
    Explanations

    when, until, or, not

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

    breakdown or step-by-step explanation

    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
    僟
    0.55
    ਫ
    0.53
     Акысыз
    0.51
     اكيد
    0.50
    obeb
    0.48
    doctor
    0.48
     kuliah
    0.48
    cccn
    0.46
    IsMethod
    0.46
     مشہور
    0.46
    POSITIVE LOGITS
     polytope
    0.42
    天
    0.40
     codebase
    0.40
    润
    0.39
    硅
    0.39
    托
    0.39
     payloads
    0.38
     Robo
    0.38
     ruck
    0.38
    <0xAD>
    0.38
    Activations Density 0.008%

    No Known Activations