© 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. 22614
    Prev
    Next
    INDEX
    Explanations

    call center

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

    "hopping" or "monomers"

    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
     attham
    0.48
     整
    0.48
    周期
    0.47
     స్థాయి
    0.47
    öny
    0.46
    ισμού
    0.46
    𒈦
    0.46
    ല്‍
    0.45
    ników
    0.45
    届
    0.44
    POSITIVE LOGITS
     y
    0.58
     quen
    0.54
     explained
    0.52
     eben
    0.45
     perdido
    0.45
     nd
    0.44
     hoş
    0.44
     las
    0.43
    antage
    0.43
     deaf
    0.42
    Activations Density 0.000%

    No Known Activations