© 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. 196115
    Prev
    Next
    INDEX
    Explanations

    business / financial / technical terms

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

    evaluation & characters

    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
    .';
    0.48
     liturgical
    0.48
     Chúa
    0.46
     LC
    0.46
     literals
    0.46
     urbana
    0.45
     as
    0.44
    .</
    0.44
     washers
    0.44
    ritt
    0.44
    POSITIVE LOGITS
    verification
    0.45
     கூட்டணிய
    0.44
    credential
    0.44
    សារ
    0.43
    Investors
    0.43
    examination
    0.43
     దాని
    0.42
    資金
    0.42
    资金
    0.42
    検証
    0.42
    Activations Density 0.001%

    No Known Activations