© 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. 96384
    Prev
    Next
    INDEX
    Explanations

    specific conjunctions followed by words

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

    indicate categorizing

    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
    aue
    0.48
     acteurs
    0.46
     você
    0.45
     advocates
    0.44
    ₺
    0.44
     muchos
    0.43
     schon
    0.43
    administ
    0.43
     einst
    0.43
     als
    0.42
    POSITIVE LOGITS
    𝒌
    0.43
    च्या
    0.43
     스테
    0.42
     Kristi
    0.42
    美麗
    0.41
     กําลัง
    0.41
     詳細
    0.41
    oramic
    0.41
     सुनकर
    0.41
     ferromagnetic
    0.41
    Activations Density 0.001%

    No Known Activations