© 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. 249110
    Prev
    Next
    INDEX
    Explanations

    current listing, control of, complete portfolio

    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
     العلام
    0.45
     BAR
    0.44
     συνα
    0.44
     menentukan
    0.44
     শব্দ
    0.44
    ੱ
    0.44
     چشم
    0.43
    ومن
    0.43
     arus
    0.43
     อุ
    0.42
    POSITIVE LOGITS
    keep
    0.55
    v
    0.55
    advertise
    0.54
    infection
    0.53
    hôte
    0.50
    difficulty
    0.49
    communicate
    0.49
    krank
    0.47
    vo
    0.47
    backend
    0.47
    Activations Density 0.000%

    No Known Activations