© 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. 56341
    Prev
    Next
    INDEX
    Explanations

    javadocs and code comments

    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
     prickly
    0.44
     chast
    0.42
     attachment
    0.41
     secondly
    0.40
    Ṕ
    0.40
     Attachment
    0.40
    Примітки
    0.40
     objectMapper
    0.39
    驄
    0.39
     छाया
    0.39
    POSITIVE LOGITS
    Did
    0.38
    edLeft
    0.38
    uang
    0.37
    瀹
    0.37
    Hang
    0.36
    WebDriver
    0.36
    ٹن
    0.35
    渡
    0.35
    Modeling
    0.35
    hang
    0.34
    Activations Density 0.004%

    No Known Activations