© 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. 5285
    Prev
    Next
    INDEX
    Explanations

    methods, environment, technologies

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

    explaining nuanced situations

    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
    ਿ
    0.47
     pInBuffer
    0.42
     envis
    0.40
    𒁍
    0.40
     envisage
    0.40
     অবশ্য
    0.38
    ጨም
    0.37
    イ
    0.37
    বিষ্য
    0.37
     இலங்க
    0.37
    POSITIVE LOGITS
    1
    0.47
    BUT
    0.43
     komfort
    0.40
    ™.
    0.40
    8
    0.39
     moderne
    0.39
     comenzamos
    0.39
     geospatial
    0.39
    9
    0.39
     Baylor
    0.38
    Activations Density 0.259%

    No Known Activations