© 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. 104018
    Prev
    Next
    INDEX
    Explanations

    necessary to

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

    potential harm or allowance

    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
    谠
    0.55
    平时
    0.53
    lastCursor
    0.51
     நாளில்
    0.51
    苏联
    0.51
     उपनिवेश
    0.50
    騇
    0.49
    मधील
    0.49
     взгляд
    0.49
     கிறிஸ்துவின்
    0.49
    POSITIVE LOGITS
     slice
    0.55
     slices
    0.53
    )
    0.52
    !
    0.52
    0.50
    .
    0.49
    >
    0.47
      
    0.47
     matching
    0.47
    Br
    0.46
    Activations Density 0.001%

    No Known Activations