© 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. 138878
    Prev
    Next
    INDEX
    Explanations

    of

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

    but possible

    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
     perpetually
    0.50
    inig
    0.47
    ɩ
    0.47
    ėje
    0.47
    ję
    0.46
     ढूंढ
    0.46
     предложение
    0.46
    alloween
    0.46
    Proposed
    0.45
    𝐝
    0.45
    POSITIVE LOGITS
     emphasizes
    0.47
    нос
    0.46
     đây
    0.46
    द्दल
    0.43
     invertebrates
    0.43
    yta
    0.42
    쌍
    0.42
     Anthropology
    0.42
     importants
    0.42
     biofilms
    0.42
    Activations Density 0.000%

    No Known Activations