© 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. 112933
    Prev
    Next
    INDEX
    Explanations

    groups and occupations

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

    probabilities and textual content

    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
    ก่อน
    0.49
    یه
    0.45
    سے
    0.44
     }}}
    0.43
    the
    0.42
    üh
    0.42
    ಣೆ
    0.41
    ◥
    0.41
    انب
    0.41
     рецеп
    0.40
    POSITIVE LOGITS
     thugs
    0.49
     laborers
    0.47
     நூ
    0.44
     heirs
    0.43
     linens
    0.43
    鿁
    0.42
     ნახ
    0.42
     oppressed
    0.42
     herm
    0.41
     కార్
    0.41
    Activations Density 0.000%

    No Known Activations