© 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. 179363
    Prev
    Next
    INDEX
    Explanations

    Japanese narration

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

    words followed by specific terms

    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
     servicemen
    0.53
     ಸುಬ್ಬ
    0.51
     stargazerCount
    0.50
     וה
    0.50
     rainforest
    0.49
     ו
    0.48
    FrameID
    0.48
     employeeService
    0.47
    amard
    0.46
     shinobi
    0.46
    POSITIVE LOGITS
    ©
    0.50
    eterm
    0.50
    U
    0.49
     Mode
    0.47
     Alternate
    0.47
    Answer
    0.45
     Straw
    0.45
     Close
    0.44
    election
    0.44
    mode
    0.43
    Activations Density 0.000%

    No Known Activations