© 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. 53-GEMMASCOPE-2-RES-262K
    7. 66453
    Prev
    Next
    INDEX
    Explanations

    total calories

    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_53_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
     however
    0.42
     cuz
    0.41
     bijvoorbeeld
    0.40
     pump
    0.40
     vf
    0.39
    vf
    0.39
     additionally
    0.38
    '],
    0.38
     toutefois
    0.38
     oke
    0.38
    POSITIVE LOGITS
    entrant
    0.45
     Visits
    0.40
     שה
    0.40
    食堂
    0.40
     ట
    0.39
     Expl
    0.39
     Dining
    0.37
    visited
    0.37
     Bennett
    0.37
     Burger
    0.37
    Activations Density 0.394%

    No Known Activations