© 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. 49738
    Prev
    Next
    INDEX
    Explanations

    strict guidelines, Class lounge, if you

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

    weekly schedule, water snakes, forearm length

    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
    ං
    0.46
    ग्रियों
    0.45
    一
    0.44
    ヴォ
    0.43
    ل
    0.42
     Tipo
    0.42
    Ӏ
    0.41
    ol
    0.41
    Ij
    0.41
    Tis
    0.40
    POSITIVE LOGITS
     आला
    0.51
     হইলাম
    0.47
     attenuated
    0.47
     который
    0.47
    शाही
    0.47
    bicycle
    0.46
     रॉयल
    0.46
     chiropractic
    0.46
     ພວກເຮົາ
    0.46
     Nietzsche
    0.46
    Activations Density 0.000%

    No Known Activations