© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3888
    Prev
    Next
    INDEX
    Explanations

    there are / int main

    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_22_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
    ]/
    0.60
    %/
    0.60
    }}/
    0.58
     जेव्हा
    0.58
    ]]);
    0.58
     وعند
    0.57
    عند
    0.57
    ].)
    0.56
    WHEN
    0.55
     ஊற
    0.54
    POSITIVE LOGITS
     Predictions
    0.69
     Numbers
    0.67
    pxy
    0.67
    预测
    0.65
     tur
    0.64
    agram
    0.64
    移動
    0.64
     газе
    0.64
    行李
    0.63
    dorff
    0.63
    Activations Density 0.112%

    No Known Activations