© 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. 84258
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by modal verbs

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

    assume breach

    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
     împ
    0.44
    깼
    0.43
     점점
    0.42
    覺
    0.41
     السي
    0.41
     내가
    0.41
    ᄊ
    0.41
     clade
    0.40
    <0xAB>
    0.40
     viewBox
    0.40
    POSITIVE LOGITS
     сможет
    0.44
    mh
    0.44
     Besonder
    0.43
     Dah
    0.42
    different
    0.41
     Rodríguez
    0.41
    <start_of_image>
    0.41
     will
    0.41
     Viele
    0.41
    ান্তি
    0.40
    Activations Density 0.001%

    No Known Activations