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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1905
    Prev
    Next
    INDEX
    Explanations

    people followed by descriptions

    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_40_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
    ()
    0.23
    2
    0.22
     setw
    0.21
     نثر
    0.21
    <b>
    0.21
    编译器
    0.21
    <bos>
    0.20
    <strong>
    0.20
     timer
    0.20
                    
    0.20
    POSITIVE LOGITS
     ktorí
    0.43
     who
    0.40
     whose
    0.38
     الذين
    0.37
     whom
    0.37
     kteří
    0.37
     którzy
    0.35
     जिन्होंने
    0.35
    whom
    0.34
    whose
    0.34
    Activations Density 0.099%

    No Known Activations