© 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. 27451
    Prev
    Next
    INDEX
    Explanations

    business opportunity

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

    moral and ritual negation

    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
    ite
    0.45
     رد
    0.44
    醃
    0.43
     Newport
    0.42
     Mexique
    0.42
    utie
    0.41
     Medina
    0.40
    κ
    0.40
     Salmon
    0.40
     Kerr
    0.40
    POSITIVE LOGITS
     estarán
    0.59
     unrivalled
    0.53
    ѳ
    0.47
     straordin
    0.46
     poderão
    0.46
     gegründ
    0.46
     pracę
    0.45
     unterstützen
    0.45
     podrán
    0.44
     unparalleled
    0.44
    Activations Density 0.000%

    No Known Activations