© 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. 160558
    Prev
    Next
    INDEX
    Explanations

    occupies five

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

    don't mistake X for Y

    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
    衵
    0.49
    member
    0.49
    Տ
    0.49
    setOn
    0.49
     ờ
    0.48
    犃
    0.47
    popsicle
    0.47
    龈
    0.46
    setStyle
    0.46
    在那
    0.46
    POSITIVE LOGITS
     questo
    0.53
     keputusan
    0.52
     his
    0.51
     remarked
    0.50
     alerted
    0.50
     livelli
    0.50
     reversed
    0.49
     meanwhile
    0.48
     deserted
    0.48
     locais
    0.47
    Activations Density 0.000%

    No Known Activations