© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 28129
    Prev
    Next
    INDEX
    Explanations

    legal permissions and assurances

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

    license and licensed

    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
    帘
    0.50
    亽
    0.49
     আইনজীব
    0.46
    MemoryWarning
    0.46
    穼
    0.46
    ঁজ
    0.45
     بينهم
    0.45
    ví
    0.44
     vínculos
    0.44
    当我们
    0.44
    POSITIVE LOGITS
     of
    0.46
    を用
    0.45
     a
    0.44
     to
    0.43
     Hanna
    0.43
     peptide
    0.43
     II
    0.41
     sektor
    0.41
     Z
    0.40
     presidente
    0.40
    Activations Density 0.000%

    No Known Activations