© 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. 248743
    Prev
    Next
    INDEX
    Explanations

    data subject

    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
    Vijay
    0.49
    archiwizowane
    0.47
    leti
    0.46
     kons
    0.46
    他还
    0.46
    ｆ
    0.46
     ফেব্রুয়ার
    0.46
    konstru
    0.45
    полу
    0.45
    ҝ
    0.44
    POSITIVE LOGITS
    </th>
    0.47
    括
    0.46
     вод
    0.45
     vinculado
    0.43
    <?
    0.42
     अन्दर
    0.42
     cuentas
    0.41
    ieza
    0.41
     centred
    0.41
     démar
    0.41
    Activations Density 0.000%

    No Known Activations