© 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. 197620
    Prev
    Next
    INDEX
    Explanations

    absorbed from

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

    specific phrases and descriptions

    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
    ላቸው
    0.52
     vasculature
    0.51
     waterways
    0.47
    cual
    0.47
    وسی
    0.45
    Volatility
    0.45
    涝
    0.44
     appointees
    0.43
     volatility
    0.43
     relações
    0.42
    POSITIVE LOGITS
    pper
    0.45
     சு
    0.45
    }=
    0.43
     Escherichia
    0.43
    ritional
    0.43
     Jeffrey
    0.43
     $\}$
    0.42
     vener
    0.41
     अनु
    0.41
    ப்பெ
    0.41
    Activations Density 0.000%

    No Known Activations