© 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. 47088
    Prev
    Next
    INDEX
    Explanations

    scar, No, Weak, research, Recovery, converted, research, when, implement

    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
     subcommittee
    0.44
     quartile
    0.43
     fibrillation
    0.43
     visualizar
    0.43
     Opinion
    0.42
     孔
    0.42
    reetype
    0.41
     Subcommittee
    0.41
     biennium
    0.41
     opinion
    0.41
    POSITIVE LOGITS
     för
    0.43
     contrôle
    0.43
    ומי
    0.42
    дио
    0.42
    över
    0.41
     орке
    0.41
    UM
    0.41
    鹦
    0.41
    勮
    0.40
    entraînement
    0.40
    Activations Density 0.002%

    No Known Activations