© 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. 60963
    Prev
    Next
    INDEX
    Explanations

    product titles or listings

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

    forces, rising, overall, events

    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
    ത്ഥ
    0.48
     inescap
    0.46
    ائیگی
    0.46
    ardır
    0.45
     Gemeinden
    0.43
    textepsilon
    0.43
    ⵅ
    0.43
    کروچ
    0.43
     beruf
    0.43
    জনের
    0.43
    POSITIVE LOGITS
    j
    0.52
    </h1>
    0.51
    aval
    0.48
     ст
    0.47
     बतौर
    0.47
    af
    0.46
    w
    0.45
    </span>
    0.44
    <0x0D>
    0.44
    over
    0.44
    Activations Density 0.000%

    No Known Activations