© 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. 54677
    Prev
    Next
    INDEX
    Explanations

    reasonably foreseeable risks

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

    early origins presentation weighing

    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
     encyclopedia
    0.46
    áže
    0.45
    cedures
    0.45
    <unused967>
    0.44
     все
    0.43
     Ле
    0.43
    следование
    0.42
    ल्ली
    0.42
    ंद्रा
    0.42
    关于
    0.42
    POSITIVE LOGITS
    itores
    0.47
     Brewing
    0.45
    ib
    0.44
     Hitt
    0.44
     Niem
    0.43
     Natürlich
    0.43
     সঞ্চ
    0.43
    そのような
    0.42
     >=
    0.42
     Thoreau
    0.42
    Activations Density 0.000%

    No Known Activations