© 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. 12829
    Prev
    Next
    INDEX
    Explanations

    Okay, let's break down

    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
    ():
    0.50
    !:
    0.49
     meliputi
    0.48
    ：
    0.47
     Include
    0.46
    :
    0.44
    ?:
    0.44
    including
    0.44
    \":
    0.44
    Includes
    0.44
    POSITIVE LOGITS
     ঘণ্টা
    0.43
    ঘাট
    0.37
    ]}.
    0.37
    哪個
    0.37
    olta
    0.37
     هناك
    0.36
    كية
    0.36
    ucin
    0.36
    <unused2119>
    0.36
    
    0.35
    Activations Density 0.141%

    No Known Activations