© 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. 205209
    Prev
    Next
    INDEX
    Explanations

    best quality

    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
    ╽
    0.46
    ли
    0.43
    íš
    0.43
    л
    0.43
     jefe
    0.42
    isição
    0.42
    endereco
    0.41
    ח
    0.41
     Bá
    0.40
    ícias
    0.40
    POSITIVE LOGITS
     durations
    0.49
     contraception
    0.44
     pedigree
    0.43
     orchestrated
    0.43
     apples
    0.42
     subsidies
    0.42
     unfounded
    0.42
     registrations
    0.42
     unrelated
    0.41
     uplift
    0.41
    Activations Density 0.002%

    No Known Activations