© 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. 129199
    Prev
    Next
    INDEX
    Explanations

    local time or demographics

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

    Absolute Decline, gouging

    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
    瑄
    0.51
    բ
    0.47
    لاسه
    0.46
    temuan
    0.45
    水电
    0.45
    nav
    0.44
    τού
    0.44
    .:
    0.44
     कांस
    0.44
    MSE
    0.44
    POSITIVE LOGITS
     erreichen
    0.59
     you
    0.54
     opting
    0.53
     る
    0.52
     PWMB
    0.51
     reaching
    0.49
     commenc
    0.48
     scratches
    0.48
     punkt
    0.48
     sticking
    0.47
    Activations Density 0.001%

    No Known Activations