© 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. 38049
    Prev
    Next
    INDEX
    Explanations

    words check, higher rank

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

    baseline, versions, key differentiator

    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
     unquestionably
    0.48
    보다는
    0.46
     संग्रह
    0.44
    время
    0.44
    の
    0.43
    ис
    0.43
    추
    0.43
    ですね
    0.42
    ἤ
    0.42
    правления
    0.42
    POSITIVE LOGITS
     bố
    0.43
     सीन
    0.42
     Scene
    0.42
    üllen
    0.42
     đọc
    0.42
     adoles
    0.41
     baş
    0.41
     xas
    0.41
     downstairs
    0.41
     pretend
    0.41
    Activations Density 0.000%

    No Known Activations