© 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. 197534
    Prev
    Next
    INDEX
    Explanations

    Manhattan NRC Resident ban

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

    breakdown to decide

    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
    Rapid
    0.47
     داری
    0.46
     кора
    0.45
     δεδο
    0.44
     ouvido
    0.43
    魎
    0.43
    舱
    0.43
    ▫
    0.43
     Holman
    0.43
    岦
    0.43
    POSITIVE LOGITS
    bar
    0.60
     परन्तु
    0.52
    바
    0.51
     bar
    0.51
     kemungkinan
    0.51
    tanggal
    0.47
    but
    0.47
    उ
    0.46
    ගෙන
    0.46
     but
    0.46
    Activations Density 0.001%

    No Known Activations