© 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. 65871
    Prev
    Next
    INDEX
    Explanations

    dangerous molds

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

    numbers and codes

    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
    бра
    0.52
    үү
    0.51
    봐
    0.47
    糅
    0.46
    는
    0.46
    侨
    0.45
    стер
    0.45
    вати
    0.44
    ндо
    0.44
     —
    0.44
    POSITIVE LOGITS
     rhythms
    0.51
     traditions
    0.50
    তাহাদের
    0.49
    ার্চ
    0.48
     localities
    0.48
     productions
    0.47
    productions
    0.47
     বিশ্ব
    0.47
     supergiants
    0.47
     mature
    0.46
    Activations Density 0.000%

    No Known Activations