© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14177
    Prev
    Next
    INDEX
    Explanations

    black color definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    0.64
    З
    0.46
    प्र
    0.45
    પ્ર
    0.44
    ल
    0.43
    র
    0.43
     здоро
    0.42
    Mah
    0.42
     jednu
    0.42
    он
    0.42
    POSITIVE LOGITS
     carburetor
    0.50
     myosin
    0.44
     neutrophil
    0.43
    ്യത
    0.42
     ferret
    0.41
    ；
    0.40
     mutex
    0.40
     reinsurance
    0.40
     storage
    0.39
     Sistema
    0.39
    Activations Density 0.010%

    No Known Activations