© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9818
    Prev
    Next
    INDEX
    Explanations

    indirect perception and effect

    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
     Nonprofit
    0.46
     başlad
    0.44
     nonprofit
    0.42
     했는데
    0.41
    贵
    0.41
     చేపట్ట
    0.40
     पहला
    0.40
    婍
    0.40
     gehad
    0.39
    年轻
    0.39
    POSITIVE LOGITS
     indirectly
    0.61
     perceived
    0.56
     indirect
    0.54
     indire
    0.54
     phenomena
    0.49
     perception
    0.49
     effects
    0.49
     Indirect
    0.49
    indirect
    0.48
     effect
    0.47
    Activations Density 0.105%

    No Known Activations