Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 125200
    Prev
    Next
    INDEX
    Explanations

    enable or cause harm

    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_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
     تعلمنا
    0.44
     የበለጠ
    0.44
     हवाले
    0.42
    stateMutability
    0.41
     ریاضی
    0.41
     বেলু
    0.41
     ڈیٹا
    0.40
    耻
    0.40
     Often
    0.39
     دلیل
    0.39
    POSITIVE LOGITS
    t
    0.46
    yka
    0.46
    jne
    0.45
    avak
    0.44
    d
    0.44
    l
    0.43
    ate
    0.42
     ପ୍ର
    0.42
    ad
    0.42
    dl
    0.42
    Activations Density 0.009%

    No Known Activations