© 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. 136921
    Prev
    Next
    INDEX
    Explanations

    Data infrastructure planning

    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
    Ά
    0.49
     árv
    0.47
     success
    0.46
     Gymn
    0.45
     songs
    0.44
     prosciutto
    0.44
     Ú
    0.43
     AGM
    0.43
     absence
    0.42
     Ά
    0.42
    POSITIVE LOGITS
    នៅក្នុង
    0.55
    unt
    0.48
    its
    0.46
    except
    0.46
    claim
    0.46
    elif
    0.45
    according
    0.45
    으로써
    0.44
    mask
    0.43
    third
    0.43
    Activations Density 0.002%

    No Known Activations