© 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. 173255
    Prev
    Next
    INDEX
    Explanations

    news and dramatic events

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

    specialized settings or distant values

    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
    紅色
    0.50
     የማይ
    0.49
    过
    0.49
     干
    0.48
     过
    0.47
    滖
    0.46
    鋰
    0.45
    红色
    0.45
    цией
    0.45
     专业
    0.45
    POSITIVE LOGITS
    rifle
    0.55
     asesinato
    0.53
    iance
    0.52
     murder
    0.51
    marvel
    0.50
    murder
    0.50
     fellow
    0.50
     director
    0.47
    rance
    0.47
     quien
    0.47
    Activations Density 0.000%

    No Known Activations