© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 60634
    Prev
    Next
    INDEX
    Explanations

    aid kit

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

    training materials and living costs

    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
    UserInput
    0.47
    Q
    0.47
    Timeout
    0.46
    Access
    0.46
    Verify
    0.46
     schematic
    0.45
    ]#
    0.45
    Connect
    0.45
    Broad
    0.44
    ()
    0.44
    POSITIVE LOGITS
     Belgi
    0.54
    㨁
    0.45
    rifugal
    0.43
     disag
    0.43
     svil
    0.43
     Belgien
    0.43
    ceme
    0.42
    দ্ভ
    0.42
     motiva
    0.42
    гія
    0.41
    Activations Density 0.000%

    No Known Activations