© 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. 31-GEMMASCOPE-2-RES-65K
    4. 20323
    Prev
    Next
    INDEX
    Explanations

    lists, options, criteria, differences

    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
     sincron
    0.54
     atmosfer
    0.48
     انسان
    0.46
     nigdy
    0.46
     atmosfera
    0.46
    asmim
    0.45
    Nunca
    0.44
    ﺿ
    0.44
     juntos
    0.44
     jamás
    0.43
    POSITIVE LOGITS
    skills
    0.47
     কিছু
    0.46
     resulted
    0.44
    due
    0.41
     although
    0.40
    improved
    0.40
    several
    0.40
    いくつかの
    0.40
     several
    0.39
     difficulty
    0.39
    Activations Density 0.033%

    No Known Activations