© 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. 150838
    Prev
    Next
    INDEX
    Explanations

    negative or not continuous

    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
     tempr
    0.44
     Specifically
    0.40
    HV
    0.40
    NAL
    0.40
    ouden
    0.39
    Probe
    0.39
    ativ
    0.39
    ();
    0.38
    c
    0.38
    e
    0.38
    POSITIVE LOGITS
     exorbit
    0.45
    roquois
    0.42
     chamomile
    0.41
     পালিয়ে
    0.41
     शहनाज
    0.41
     अग्
    0.41
    姬
    0.40
     अनाउंस
    0.40
     উদ্বাস্তু
    0.39
     caffè
    0.39
    Activations Density 0.000%

    No Known Activations