© 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. 156872
    Prev
    Next
    INDEX
    Explanations

    add yourself, monitor, like, search, CDROM

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

    wanting to be

    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
    0
    0.48
     visitantes
    0.42
     negotiator
    0.42
    gst
    0.42
    1
    0.41
     visiting
    0.41
     major
    0.40
     cam
    0.40
     CAM
    0.40
     aged
    0.40
    POSITIVE LOGITS
    anderen
    0.52
    ították
    0.50
    旯
    0.47
    arrants
    0.47
    ედერ
    0.47
     périph
    0.46
    antwoord
    0.46
     MinMaxScaler
    0.46
    जेक्ट
    0.45
    étale
    0.45
    Activations Density 0.000%

    No Known Activations