© 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. 1558
    Prev
    Next
    INDEX
    Explanations

    this is

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

    This followed by an action or descriptor

    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
     andra
    0.19
     postérieures
    0.19
     einschließlich
    0.19
     autres
    0.18
    今年は
    0.18
    .’’
    0.18
     gült
    0.18
    ’
    0.18
    }^{\
    0.18
     Benutz
    0.18
    POSITIVE LOGITS
     విధంగా
    0.26
     latter
    0.23
    现象
    0.21
     konuda
    0.19
     phenomenon
    0.19
     변화
    0.19
    現象
    0.19
    רי
    0.19
     কাজটি
    0.19
     happening
    0.19
    Activations Density 0.764%

    No Known Activations