© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 34713
    Prev
    Next
    INDEX
    Explanations

    freckles and moles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̻
    0.40
     краё
    0.39
    واعد
    0.38
     ব্যবস্থাপনা
    0.38
     explotación
    0.37
    paste
    0.37
     горя
    0.37
    swf
    0.37
    र्जी
    0.37
    rubyg
    0.36
    POSITIVE LOGITS
     moles
    1.27
     mole
    1.21
     Mole
    1.14
    痣
    1.04
    Mole
    0.99
    mole
    0.98
    Moles
    0.97
     freck
    0.96
     tattoos
    0.74
     scars
    0.74
    Activations Density 0.003%

    No Known Activations