© 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. 116885
    Prev
    Next
    INDEX
    Explanations

    guide and

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

    motor, grows

    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
    煌
    0.51
    色々
    0.50
    τώ
    0.49
    中の
    0.47
    marginTop
    0.46
    いろいろ
    0.44
     केश
    0.44
    ología
    0.44
    名古屋
    0.44
    醌
    0.44
    POSITIVE LOGITS
    EM
    0.52
    💭
    0.52
     METHOD
    0.50
     estimada
    0.48
     SHE
    0.46
     kontrak
    0.45
     AID
    0.45
    😡
    0.44
     HVAC
    0.43
     WATTS
    0.43
    Activations Density 0.001%

    No Known Activations