© 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. 81939
    Prev
    Next
    INDEX
    Explanations

    crucial

    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
     잔
    0.54
     воз
    0.51
    <unused248>
    0.51
    🥲
    0.50
     산
    0.49
     बधाई
    0.48
    !।
    0.48
     предпочита
    0.48
    𓂃
    0.47
     견
    0.47
    POSITIVE LOGITS
    0.49
     Promises
    0.45
    j
    0.44
    أم
    0.44
    itor
    0.43
    ral
    0.43
    LEX
    0.42
     stressed
    0.42
    ண்டை
    0.42
     demok
    0.40
    Activations Density 0.003%

    No Known Activations