© 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. 157298
    Prev
    Next
    INDEX
    Explanations

    hand, trumpet, no doubt

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

    contrasting or conditional clauses

    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
     nessun
    0.51
    ruari
    0.50
    ຣ
    0.50
     varit
    0.49
     Pyaar
    0.49
    bido
    0.49
    jakan
    0.48
    AllRef
    0.48
    hatian
    0.48
     kaleidoscopic
    0.48
    POSITIVE LOGITS
    筋
    0.44
    消化
    0.41
    習慣
    0.40
     can
    0.40
    大丈夫
    0.40
    適
    0.39
     التمثيل
    0.38
    <0x80>
    0.38
    ヒ
    0.37
    とい
    0.37
    Activations Density 0.001%

    No Known Activations