© 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. 126993
    Prev
    Next
    INDEX
    Explanations

    business valuation and networking

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

    descriptive adjectives and states

    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
    attle
    0.49
    riebe
    0.47
    riendo
    0.46
    nombre
    0.45
    that
    0.44
    往
    0.43
    imos
    0.43
    ierno
    0.42
    고
    0.42
    reached
    0.42
    POSITIVE LOGITS
    <0xCA>
    0.47
    ენტ
    0.47
     Valuation
    0.46
     femei
    0.45
     doby
    0.44
    ઞ
    0.44
     روا
    0.43
     $_{\
    0.43
     $^{\
    0.42
    Dim
    0.42
    Activations Density 0.001%

    No Known Activations