© 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. 20564
    Prev
    Next
    INDEX
    Explanations

    researchers and their work

    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
     言っ
    0.44
     нә
    0.42
     見
    0.39
     యొక్క
    0.39
     homomorphism
    0.38
    彫
    0.38
     下さい
    0.38
     म्हणाले
    0.38
    अभ
    0.38
    OLOGIE
    0.38
    POSITIVE LOGITS
     and
    0.61
     et
    0.60
     và
    0.52
     ও
    0.50
    และ
    0.49
     και
    0.46
     و
    0.45
     и
    0.42
     மற்றும்
    0.41
     एवं
    0.40
    Activations Density 0.004%

    No Known Activations