© 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. 198139
    Prev
    Next
    INDEX
    Explanations

    already offer, musical bond, winner plus

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

    legacy and ethics

    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
     custodian
    0.48
    کار
    0.48
     activos
    0.46
    ਰ
    0.45
    ائے
    0.44
     appended
    0.43
    ವರ್
    0.43
     custodial
    0.43
    تی
    0.41
    Cristiano
    0.41
    POSITIVE LOGITS
    ።
    0.51
    );
    0.50
    ),
    0.47
    ęg
    0.46
     దు
    0.45
    oled
    0.45
     sinister
    0.45
    >>,
    0.45
     recto
    0.44
     çağ
    0.44
    Activations Density 0.002%

    No Known Activations