© 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. 38543
    Prev
    Next
    INDEX
    Explanations

    minimally invasive technique

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

    describing future possibilities or enhanced features

    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
     ш
    0.50
    仴
    0.50
     விகி
    0.49
     বণ্ট
    0.48
     бра
    0.48
     гру
    0.48
     ло
    0.45
     есте
    0.45
     szüks
    0.45
     в
    0.45
    POSITIVE LOGITS
    relativistic
    0.48
    immers
    0.46
     envisioned
    0.43
    sustainable
    0.43
    firebase
    0.43
     nondestructive
    0.42
    5
    0.42
    ses
    0.41
     futuristic
    0.41
    promised
    0.41
    Activations Density 0.000%

    No Known Activations