© 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. 41079
    Prev
    Next
    INDEX
    Explanations

    selection of single system television map site

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

    providing directions, providing libraries, links to

    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
    )},
    0.48
    },
    0.47
     tions
    0.47
    hos
    0.43
     as
    0.42
    ED
    0.42
    vah
    0.41
    )}.
    0.40
    bla
    0.40
    kter
    0.40
    POSITIVE LOGITS
    ړو
    0.59
     humides
    0.57
    Tuple
    0.51
     শরীরের
    0.49
     جما
    0.48
     सर्
    0.47
    illez
    0.47
    𒊩
    0.46
     condiment
    0.46
     زاويه
    0.46
    Activations Density 0.000%

    No Known Activations