© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1853
    Prev
    Next
    INDEX
    Explanations

    I don't

    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
     strings
    0.41
    ToString
    0.40
     строк
    0.40
    String
    0.39
     Strings
    0.39
    strings
    0.38
    Font
    0.38
    м
    0.37
    ং
    0.37
    旄
    0.37
    POSITIVE LOGITS
     indirectly
    0.54
     indire
    0.53
     apoyo
    0.52
     cognizant
    0.52
     apoyar
    0.51
    覬
    0.51
     interesse
    0.49
     bantu
    0.49
     recognising
    0.48
     zainteres
    0.48
    Activations Density 0.826%

    No Known Activations