© 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. 197320
    Prev
    Next
    INDEX
    Explanations

    places or specific locations

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

    provide parameter request list

    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
     Architecture
    0.51
     或
    0.50
     🌱
    0.49
    퇸
    0.49
     drawable
    0.46
     entry
    0.46
     we
    0.46
     dwt
    0.45
    我们可以
    0.44
    𝖽
    0.44
    POSITIVE LOGITS
     সেখানকার
    0.56
     عندما
    0.52
     صدا
    0.52
     आवाज
    0.49
     humiliated
    0.48
     hesitated
    0.47
    otland
    0.45
     ridiculed
    0.45
     scru
    0.45
     mengatakan
    0.44
    Activations Density 0.001%

    No Known Activations