© 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. 53803
    Prev
    Next
    INDEX
    Explanations

    own risk

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

    Mobile App Development, TikTok

    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
     deduction
    0.46
    usam
    0.46
     olim
    0.45
     v
    0.44
    梠
    0.44
     দিল
    0.44
    äts
    0.44
     smile
    0.42
     coral
    0.42
    omaly
    0.42
    POSITIVE LOGITS
    ﺰ
    0.52
    การ
    0.51
     Jej
    0.50
     συνο
    0.49
     важней
    0.46
    အတွ
    0.46
    ﺘ
    0.45
    蕃
    0.45
    続いて
    0.44
    дування
    0.44
    Activations Density 0.001%

    No Known Activations