© 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. 46501
    Prev
    Next
    INDEX
    Explanations

    Terra, facts, and foreign words

    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
    permission
    0.45
    )=(\
    0.38
    Methoxy
    0.37
     commandment
    0.37
    াওয়া
    0.36
    PERMISSION
    0.36
     eş
    0.36
     신경
    0.36
    __)
    0.35
    留意
    0.35
    POSITIVE LOGITS
    formulas
    0.40
     हमने
    0.39
    ูก
    0.39
    才有
    0.38
     Facts
    0.38
     গৌর
    0.38
    Terra
    0.38
    terra
    0.37
     тер
    0.37
    facts
    0.37
    Activations Density 0.000%

    No Known Activations