© 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. 220387
    Prev
    Next
    INDEX
    Explanations

    specific entities or terms

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

    Dynamic Island

    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
    త్తు
    0.47
     accepted
    0.46
    婄
    0.46
     ሲ
    0.46
    烧
    0.45
    accepted
    0.44
     لما
    0.44
     지속
    0.44
    嶂
    0.44
    еха
    0.44
    POSITIVE LOGITS
    letak
    0.45
     svært
    0.45
     viele
    0.44
     immortal
    0.43
     inoxid
    0.42
     ete
    0.42
    Lähteet
    0.41
     Muit
    0.41
     incumbent
    0.41
     इथे
    0.40
    Activations Density 0.000%

    No Known Activations