© 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. 26378
    Prev
    Next
    INDEX
    Explanations

    constant calls, look forward to

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

    abuse and harm

    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
    <unused2148>
    0.44
     सलाहकार
    0.42
    좔
    0.42
    ण्
    0.41
    acrylic
    0.40
    idential
    0.40
    uncertain
    0.40
    applicants
    0.40
    ilets
    0.40
    า
    0.40
    POSITIVE LOGITS
     h
    0.43
     roused
    0.43
     Sumb
    0.42
     către
    0.42
     Lander
    0.42
     Sumatra
    0.41
     Sumatera
    0.41
     سەر
    0.40
     spindle
    0.40
     decimated
    0.40
    Activations Density 0.000%

    No Known Activations