© 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. 236717
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
    และ
    0.48
     and
    0.43
    以及
    0.43
     alongside
    0.42
    ãs
    0.41
    0.40
    そして
    0.40
    ando
    0.39
    1
    0.39
    ø
    0.39
    POSITIVE LOGITS
    笥
    0.46
    ঞ্চল্য
    0.44
     použí
    0.42
    রীণ
    0.41
     ঘরের
    0.41
     svého
    0.40
     nhờ
    0.39
     ஒன்றை
    0.39
    ្នែក
    0.39
     सहारे
    0.39
    Activations Density 0.040%

    No Known Activations