© 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. 52976
    Prev
    Next
    INDEX
    Explanations

    increased security, clear communication, illegal

    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
    Kids
    0.41
     বাড়ানো
    0.41
     ][
    0.40
     %)
    0.39
     April
    0.38
    قبل
    0.38
    Move
    0.37
     interesado
    0.37
     Masyarakat
    0.37
    kids
    0.37
    POSITIVE LOGITS
    ทำให้
    0.47
     만들
    0.46
     menacing
    0.45
     meaningless
    0.43
     생성
    0.43
    UTF
    0.42
    UREMENT
    0.41
    毌
    0.41
    아트
    0.41
    aktan
    0.41
    Activations Density 0.019%

    No Known Activations