© 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. 131700
    Prev
    Next
    INDEX
    Explanations

    longer than

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

    code logic and documentation

    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
     интен
    0.46
    ING
    0.45
    ricao
    0.45
    žem
    0.43
     BlueprintName
    0.43
     형태
    0.42
    ³)
    0.42
     Phong
    0.42
    ParameterActive
    0.42
     의
    0.41
    POSITIVE LOGITS
     polin
    0.48
     YG
    0.46
     KOM
    0.44
    ابر
    0.44
     supplies
    0.44
     maximization
    0.44
     grafts
    0.44
     stipulated
    0.43
    ض
    0.43
     WG
    0.43
    Activations Density 0.000%

    No Known Activations