© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78533
    Prev
    Next
    INDEX
    Explanations

    dependent onsubject torectanglesmotorcyclebetter

    np_acts-logits-general · gemini-2.5-flash-lite

    clarity and specificity of narrative or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鐏
    0.56
    क्टी
    0.53
    薁
    0.52
    炁
    0.51
    نيا
    0.51
    槅
    0.51
    Therates
    0.50
    齐
    0.50
    徂
    0.50
    ચ્
    0.49
    POSITIVE LOGITS
    ba
    0.57
    aba
    0.48
    mn
    0.48
    mos
    0.48
     unstructured
    0.48
    sa
    0.47
    s
    0.47
    d
    0.46
    .
    0.46
    ta
    0.46
    Activations Density 0.000%

    No Known Activations