© 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. 124471
    Prev
    Next
    INDEX
    Explanations

    giveaway new opportunity

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

    explores themes and connections

    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
     soggiorno
    0.48
    脅
    0.46
     які
    0.43
     fiancé
    0.43
     سؤال
    0.43
     س
    0.42
    colorControl
    0.42
     thug
    0.41
     कमरे
    0.41
    ដែលមាន
    0.41
    POSITIVE LOGITS
    lcii
    0.52
    avorites
    0.47
    OrCallback
    0.47
    lL
    0.46
     wszyst
    0.46
    饨
    0.44
    tochy
    0.43
    和服务
    0.43
     shēng
    0.43
     odby
    0.43
    Activations Density 0.000%

    No Known Activations