© 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. 38310
    Prev
    Next
    INDEX
    Explanations

    events and relationships

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

    hopeless romantic, German birthday, invitations

    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
    وري
    0.46
    龔
    0.45
    碼
    0.45
    競爭
    0.45
     cybersecurity
    0.44
    粉絲
    0.44
    焐
    0.44
    媧
    0.43
    塩
    0.43
    氀
    0.43
    POSITIVE LOGITS
    coloured
    0.46
     watercolour
    0.46
     rangkaian
    0.46
     Colour
    0.44
    ılmış
    0.44
    成り
    0.44
     oars
    0.43
     sorrows
    0.43
     homely
    0.42
     Izv
    0.42
    Activations Density 0.009%

    No Known Activations