© 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. 84856
    Prev
    Next
    INDEX
    Explanations

    addressed to you

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

    words after comma

    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
    弇
    0.44
    চ্ছুক
    0.42
    行
    0.41
     automaticamente
    0.40
    厨
    0.40
    लेल्या
    0.40
    】,
    0.40
     `>=`,
    0.40
    廚
    0.39
    enderung
    0.39
    POSITIVE LOGITS
     you
    0.47
     slander
    0.46
     renowned
    0.45
    you
    0.44
     nowe
    0.44
     тобой
    0.41
     इन्हीं
    0.41
    فر
    0.40
    你说
    0.40
     your
    0.39
    Activations Density 0.083%

    No Known Activations