© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 135837
    Prev
    Next
    INDEX
    Explanations

    week ending, text generation

    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
     sleek
    0.52
     wallet
    0.48
     brand
    0.46
    קס
    0.46
    }`);
    0.45
     calorie
    0.45
     frictionless
    0.45
     мо
    0.44
     Avant
    0.44
     siku
    0.44
    POSITIVE LOGITS
    PAC
    0.46
    வெ
    0.46
    仍然
    0.44
    ási
    0.43
    marshaller
    0.43
    见
    0.42
    ographique
    0.41
    基础设施
    0.41
    ']),
    0.40
    㓈
    0.40
    Activations Density 0.000%

    No Known Activations