© 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. 182118
    Prev
    Next
    INDEX
    Explanations

    activity from

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

    historical context or descriptions

    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
    ન
    0.47
    t
    0.46
    ুকু
    0.44
     scom
    0.43
    سال
    0.43
    s
    0.42
     sucess
    0.42
     sensed
    0.41
    স
    0.41
    ità
    0.40
    POSITIVE LOGITS
     ".$
    0.54
     PhoneNumber
    0.51
    atform
    0.48
    TTY
    0.47
     จึง
    0.47
     गिवन
    0.47
    ۝
    0.46
     dialects
    0.45
    ?.
    0.45
     เฉล
    0.44
    Activations Density 0.000%

    No Known Activations