© 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. 16-GEMMASCOPE-2-RES-262K
    7. 820
    Prev
    Next
    INDEX
    Explanations

    homework and assignments

    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_16_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
    ד
    0.58
    지
    0.48
    קס
    0.45
    ม
    0.45
    ט
    0.43
    ”.
    0.42
    та
    0.42
    يه
    0.42
    .”
    0.42
    ය
    0.42
    POSITIVE LOGITS
     něm
    0.42
    مس
    0.41
     větší
    0.40
    فر
    0.39
     xếp
    0.39
    sl
    0.38
    ères
    0.38
     conseguido
    0.38
     près
    0.38
    ся
    0.37
    Activations Density 0.000%

    No Known Activations