© 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. 38558
    Prev
    Next
    INDEX
    Explanations

    member if, of TYPE, as Retail, Story by

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

    places or people

    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
     intimidate
    0.46
    }}\
    0.44
     countenance
    0.44
     Ра
    0.43
    కార
    0.43
    كبر
    0.42
    }}$$
    0.42
    auche
    0.40
    кен
    0.39
     missp
    0.39
    POSITIVE LOGITS
     puisque
    0.49
    綸
    0.47
     wären
    0.46
    に戻
    0.44
     presenceData
    0.43
     वाहत
    0.43
    发布的
    0.42
     poiché
    0.42
    ysin
    0.41
     cytoplasmic
    0.41
    Activations Density 0.000%

    No Known Activations