© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 12794
    Prev
    Next
    INDEX
    Explanations

    describing usual situations

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

    describing typical characteristics

    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
    </h3>
    0.83
     as
    0.81
    </h2>
    0.78
    </h1>
    0.77
     and
    0.77
    <0x0D>
    0.75
    </h4>
    0.75
     been
    0.73
     l
    0.69
     e
    0.69
    POSITIVE LOGITS
    ра
    0.75
    지만
    0.75
    ين
    0.68
    funcionario
    0.66
    시
    0.66
     보통
    0.65
    तां
    0.64
     때는
    0.64
    ü
    0.63
    가
    0.63
    Activations Density 0.051%

    No Known Activations