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. 26171
    Prev
    Next
    INDEX
    Explanations

    Arabic literature Qur'an

    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
     terrible
    0.50
    💣
    0.49
     infamous
    0.48
     horrible
    0.46
    ิล
    0.45
    销量
    0.45
     🔥
    0.45
     '';
    0.43
     dodgy
    0.43
     কোথায়
    0.43
    POSITIVE LOGITS
    ad
    0.63
    were
    0.58
     alumna
    0.50
    ae
    0.50
    ir
    0.49
    ch
    0.48
    considered
    0.48
    pps
    0.48
    7
    0.47
    ce
    0.46
    Activations Density 0.002%

    No Known Activations