© 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. 107036
    Prev
    Next
    INDEX
    Explanations

    modality or state

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

    instructions, arguments, or sensitive topics

    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
    CAMP
    0.50
    मंद
    0.47
    band
    0.46
    chef
    0.45
    밴
    0.45
    嫣
    0.44
    陝
    0.44
    𝗰
    0.44
    𝙢
    0.44
    sweet
    0.44
    POSITIVE LOGITS
    abled
    0.44
    ontaneous
    0.44
     مضمون
    0.42
    及时
    0.42
     μεταξύ
    0.41
     kịp
    0.41
     Guided
    0.41
    க்கை
    0.41
    ability
    0.41
     நடை
    0.40
    Activations Density 0.001%

    No Known Activations