© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92969
    Prev
    Next
    INDEX
    Explanations

    interface names starting with I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UserManager
    -0.90
     UserController
    -0.77
     UserRepository
    -0.76
     ItemType
    -0.76
    identifiers
    -0.73
    liğini
    -0.73
    ETERS
    -0.73
    ｳ
    -0.73
     McInt
    -0.73
     HttpStatus
    -0.72
    POSITIVE LOGITS
     I
    3.16
     IS
    2.19
     IM
    2.03
     IA
    1.97
     IT
    1.94
    IS
    1.84
     IP
    1.81
     IB
    1.80
    IC
    1.80
     IG
    1.79
    Activations Density 0.207%

    No Known Activations