© 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. 220221
    Prev
    Next
    INDEX
    Explanations

    ; and ,

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

    musical intros

    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
    7
    0.53
     recalc
    0.52
    4
    0.51
    جی
    0.50
     voltou
    0.50
     incentiv
    0.49
    6
    0.49
     nirvach
    0.48
     चिन्ह
    0.48
     icch
    0.47
    POSITIVE LOGITS
    স্
    0.51
    Slot
    0.45
    sz
    0.44
    Arte
    0.43
    罨
    0.43
    ন্ত্রণ
    0.43
    Rig
    0.43
    Deployment
    0.42
    Haupt
    0.42
    Sched
    0.42
    Activations Density 0.001%

    No Known Activations