© 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. 116927
    Prev
    Next
    INDEX
    Explanations

    material, beliefs, events, status, action

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

    different language concepts

    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
     ming
    0.51
    ទៅ
    0.50
     hè
    0.48
     dentist
    0.47
    能
    0.46
     đi
    0.44
     thờ
    0.44
     geld
    0.43
     lehet
    0.43
     blood
    0.43
    POSITIVE LOGITS
    keyValue
    0.45
    ämään
    0.45
     초기
    0.45
    aviti
    0.44
    эле
    0.44
    ინა
    0.44
    纰
    0.44
    必要な
    0.44
    કરણ
    0.43
    ματος
    0.43
    Activations Density 0.002%

    No Known Activations