© 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. 61665
    Prev
    Next
    INDEX
    Explanations

    geographic locations

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

    implied volatility calculation

    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
    ാനും
    0.44
    玥
    0.43
    热爱
    0.41
    珩
    0.40
    AuthState
    0.40
    沔
    0.40
    多元
    0.39
    渚
    0.39
    珉
    0.39
    ូម
    0.39
    POSITIVE LOGITS
     accelerator
    0.51
    ax
    0.49
     pathology
    0.47
     accelerators
    0.47
     tissues
    0.46
    avana
    0.46
     calcula
    0.45
    are
    0.45
     acel
    0.45
     pasta
    0.44
    Activations Density 0.000%

    No Known Activations