© 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. 197622
    Prev
    Next
    INDEX
    Explanations

    digital photography, gay men, own photos

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

    opportunities to

    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
    ୈ
    0.52
    ហ
    0.49
    ষ্টা
    0.48
     fazla
    0.48
     シェ
    0.46
     અભ
    0.46
     consecuencias
    0.44
     asla
    0.44
    FAMILY
    0.44
    щенко
    0.43
    POSITIVE LOGITS
    m
    0.59
    emens
    0.51
     نفسها
    0.49
    م
    0.48
     parar
    0.47
     الفعل
    0.46
    د
    0.45
    platform
    0.45
    provision
    0.45
     اللغة
    0.44
    Activations Density 0.001%

    No Known Activations