© 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. 7744
    Prev
    Next
    INDEX
    Explanations

    for + noun/pronoun

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

    purpose or context

    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
    in
    0.44
    y
    0.37
    es
    0.34
     eller
    0.31
    O
    0.30
    I
    0.30
    aç
    0.29
    ed
    0.29
     vagy
    0.29
    ة
    0.28
    POSITIVE LOGITS
     this
    0.25
     a
    0.22
    творе
    0.22
    ዚህ
    0.21
    сно
    0.21
    ked
    0.21
    вости
    0.21
     приобре
    0.21
     be
    0.21
     the
    0.20
    Activations Density 0.731%

    No Known Activations