© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54464
    Prev
    Next
    INDEX
    Explanations

    study research find lecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doit
    0.55
     financi
    0.49
     Finance
    0.48
    蛆
    0.46
     Commerce
    0.46
     commerce
    0.46
     newspapers
    0.46
     negozi
    0.45
     finanzi
    0.45
     Classics
    0.44
    POSITIVE LOGITS
    Departamento
    0.44
    }=-\
    0.42
    Př
    0.42
    peptide
    0.42
     ligands
    0.42
    १८
    0.41
    гали
    0.41
    ческое
    0.41
    Während
    0.41
    ucle
    0.41
    Activations Density 0.002%

    No Known Activations