© 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. 152052
    Prev
    Next
    INDEX
    Explanations

    ban, banner, or arbit"}

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

    ban / bann / banner

    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
    ゛
    0.50
     combate
    0.50
     Mudah
    0.50
    晫
    0.47
    طلع
    0.47
     Stich
    0.47
    льным
    0.46
    ፍተኛ
    0.46
     délais
    0.46
    <unused47>
    0.46
    POSITIVE LOGITS
    <0xC2>
    0.52
    BAN
    0.49
    aber
    0.48
    ban
    0.47
    banner
    0.46
    arbit
    0.46
    es
    0.46
    in
    0.45
    omar
    0.45
    és
    0.44
    Activations Density 0.000%

    No Known Activations