© 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. 182224
    Prev
    Next
    INDEX
    Explanations

    disc tray

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

    creating zip archives

    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
    ޑ
    0.49
    d
    0.48
    transitions
    0.47
     cornerback
    0.46
    rock
    0.46
    groups
    0.45
     caver
    0.45
    github
    0.45
     nhóm
    0.45
     sagittal
    0.45
    POSITIVE LOGITS
    ैव
    0.47
     而
    0.46
    !»
    0.45
     без
    0.44
    㓩
    0.44
    資金
    0.44
     അതേ
    0.44
    用的
    0.43
    碐
    0.43
     влияния
    0.42
    Activations Density 0.000%

    No Known Activations