© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 17778
    Prev
    Next
    INDEX
    Explanations

    coefficients in equations

    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_40_width_262k_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
    enste
    0.43
     pelaksanaan
    0.38
     Mikolai
    0.36
     utiliser
    0.36
    经
    0.36
    얇
    0.36
    ensatz
    0.35
    kräft
    0.35
     clust
    0.34
     Monsieur
    0.34
    POSITIVE LOGITS
     constants
    0.70
     constant
    0.64
    Constant
    0.60
     Constant
    0.59
    constants
    0.52
     constantes
    0.49
    constant
    0.48
    常量
    0.48
    常
    0.47
     costante
    0.46
    Activations Density 0.014%

    No Known Activations