© 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-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 11415
    Prev
    Next
    INDEX
    Explanations

    betrayal, pound, Click, IV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    }=$
    0.77
    توا
    0.75
    !';
    0.73
     Barrier
    0.72
     Celebrate
    0.72
     Communicate
    0.72
     Conquer
    0.70
     દ
    0.70
     celebrate
    0.70
     Watch
    0.69
    POSITIVE LOGITS
    Most
    1.11
    Additional
    0.99
    Eth
    0.93
    Selain
    0.91
    Neither
    0.91
    Because
    0.90
    ethical
    0.90
     Nesse
    0.90
    Madame
    0.90
    However
    0.89
    Activations Density 0.001%

    No Known Activations