© 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. 156995
    Prev
    Next
    INDEX
    Explanations

    monthly schedule templates

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

    am successful

    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
    اٹ
    0.45
    𝐚
    0.45
    থাৎ
    0.44
     проведения
    0.43
    ubj
    0.43
    山的
    0.43
    ванию
    0.43
    विड
    0.43
     restorations
    0.42
    >(</
    0.42
    POSITIVE LOGITS
     kompak
    0.46
    }...
    0.45
     Hudson
    0.45
     F
    0.44
     Angus
    0.43
     niece
    0.42
     number
    0.41
     Davis
    0.41
     ...
    0.41
     einen
    0.41
    Activations Density 0.000%

    No Known Activations