© 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. 36713
    Prev
    Next
    INDEX
    Explanations

    organizations, projects, or components

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

    AI platforms and models

    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
     coolest
    0.47
    もあった
    0.47
     wer
    0.47
     CLEAR
    0.46
     ChAT
    0.45
    甫
    0.45
    COOL
    0.44
     TRAN
    0.44
    ゥ
    0.44
     coexist
    0.43
    POSITIVE LOGITS
    }
    0.53
    专辑
    0.45
    RouterModule
    0.44
    Motors
    0.44
    shopify
    0.43
     sqlalchemy
    0.41
    ‌
    0.41
    窅
    0.41
     motorsport
    0.41
     पास
    0.40
    Activations Density 0.000%

    No Known Activations