© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126900
    Prev
    Next
    INDEX
    Explanations

    What questions

    np_acts-logits-general · gemini-2.5-flash-lite

    code output indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INSTR
    0.46
     caos
    0.46
    ராய
    0.45
    ாயம்
    0.45
     chaos
    0.44
     chemin
    0.44
    FOUR
    0.44
    7
    0.43
     семь
    0.43
    ৭
    0.42
    POSITIVE LOGITS
    ("["
    0.45
    лке
    0.41
     Stimme
    0.41
    提出的
    0.41
     बयान
    0.40
    ിക്കു
    0.40
     cümle
    0.40
    郎
    0.39
    نا
    0.39
    ，“
    0.39
    Activations Density 0.000%

    No Known Activations