© 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. 223410
    Prev
    Next
    INDEX
    Explanations

    general phrases and specific terms

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

    essential components or necessities

    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
    AUTO
    0.46
     Không
    0.45
    auts
    0.45
     ያል
    0.43
     સંબંધ
    0.43
     無
    0.42
     δυνα
    0.42
    ott
    0.41
    anta
    0.41
    agar
    0.41
    POSITIVE LOGITS
    𝘨
    0.49
    𝔾
    0.49
    گ
    0.48
     ছবিতে
    0.47
     оттен
    0.47
     envision
    0.47
    িনবার্গ
    0.46
     logins
    0.46
    пі
    0.46
     fondos
    0.46
    Activations Density 0.001%

    No Known Activations