© 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. 95305
    Prev
    Next
    INDEX
    Explanations

    data stored

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

    store lengths or distances

    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
     leaky
    0.46
     radios
    0.45
     destro
    0.44
    更大的
    0.43
     bó
    0.43
    ็อก
    0.43
    [++
    0.42
     slowest
    0.42
    ബരി
    0.42
     pravi
    0.42
    POSITIVE LOGITS
     Een
    0.51
     Pathology
    0.47
    .<
    0.47
     inadequacy
    0.46
     Administration
    0.46
     acknowledgement
    0.46
     Organizational
    0.46
    erit
    0.45
     विगत
    0.45
    LD
    0.45
    Activations Density 0.001%

    No Known Activations