© 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. 124610
    Prev
    Next
    INDEX
    Explanations

    want to read

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

    linked or potentially turning

    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
     منظم
    0.55
    τυχ
    0.54
    ୈ
    0.53
    θη
    0.51
     regolare
    0.51
    ρης
    0.51
     потрібно
    0.49
    Ϣ
    0.48
    ξι
    0.48
    MktCap
    0.48
    POSITIVE LOGITS
    an
    0.54
     ஓர்
    0.47
     Englishman
    0.46
     Neuro
    0.46
     Lea
    0.46
     RUD
    0.46
    ppin
    0.46
     Frenchman
    0.44
    </h2>
    0.44
    </b>
    0.43
    Activations Density 0.001%

    No Known Activations