© 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. 161307
    Prev
    Next
    INDEX
    Explanations

    achieved

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

    maximum value, visitor to

    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
     agonist
    0.57
     개
    0.55
     arginine
    0.55
     agonists
    0.54
     antiviral
    0.53
     leukocyte
    0.53
     oct
    0.52
    minLength
    0.50
     anthrac
    0.50
     epinephrine
    0.49
    POSITIVE LOGITS
     Consistent
    0.48
    <0x86>
    0.48
    挂
    0.46
    лом
    0.46
    Consistent
    0.46
    游
    0.45
    Jesus
    0.44
    লাইয়া
    0.44
    i
    0.44
    𝘐
    0.43
    Activations Density 0.000%

    No Known Activations