© 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. 40-GEMMASCOPE-2-RES-262K
    7. 165224
    Prev
    Next
    INDEX
    Explanations

    heh heh

    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_40_width_262k_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
    你
    0.49
     nigga
    0.42
     veux
    0.41
     merda
    0.41
     youre
    0.40
     YOU
    0.40
    めっちゃ
    0.40
    你要
    0.40
    爣
    0.40
     wow
    0.39
    POSITIVE LOGITS
     chuckle
    0.50
    angles
    0.47
    arity
    0.45
    sigh
    0.44
    grin
    0.44
     grin
    0.43
    ered
    0.43
    act
    0.42
     பெரு
    0.42
    smiling
    0.42
    Activations Density 0.002%

    No Known Activations