© 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. 36170
    Prev
    Next
    INDEX
    Explanations

    heteroscedasticity homoscedasticity

    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
    Hasher
    0.44
     impeach
    0.41
    嬴
    0.40
     nigga
    0.40
    цов
    0.39
    himanyu
    0.39
    mäßig
    0.38
     ListNode
    0.37
     semidefinite
    0.37
     cursorPos
    0.36
    POSITIVE LOGITS
     EXPERIENCE
    0.53
    ק
    0.52
    國
    0.49
    อ
    0.46
    南
    0.45
     K
    0.44
    O
    0.44
    א
    0.44
    vo
    0.43
     во
    0.42
    Activations Density 0.003%

    No Known Activations