© 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. 107477
    Prev
    Next
    INDEX
    Explanations

    discussing general topics

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

    inference vs software

    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
    9
    0.46
    த்தன
    0.43
    点评
    0.42
    κει
    0.42
    正确的
    0.41
    Hình
    0.41
    产
    0.41
    잤
    0.41
    颏
    0.41
    resp
    0.41
    POSITIVE LOGITS
     untapped
    0.54
     scammers
    0.52
    apatkan
    0.50
     пытается
    0.50
     conceded
    0.50
     revanche
    0.49
     enshrined
    0.49
     einer
    0.48
     recapture
    0.48
     reimag
    0.48
    Activations Density 0.002%

    No Known Activations