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-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 2632
    Prev
    Next
    INDEX
    Explanations

    code structure keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    కొని
    0.68
    కుండా
    0.68
    ípios
    0.68
    ㄶ
    0.68
    াকাছি
    0.68
     relações
    0.68
    frying
    0.64
    posição
    0.64
    ObjectTemp
    0.63
    Mé
    0.63
    POSITIVE LOGITS
     adlı
    0.92
     ซึ่ง
    0.81
    _
    0.80
     ()
    0.79
    ↵
    0.78
    .
    0.77
     LLC
    0.76
     ltd
    0.75
    .”
    0.74
     नामक
    0.74
    Activations Density 0.010%

    No Known Activations