© 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. 62324
    Prev
    Next
    INDEX
    Explanations

    making a list

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

    company morale, options given

    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
     može
    0.47
    けた
    0.46
     basiert
    0.46
    হইল
    0.46
    鈁
    0.46
     entschieden
    0.45
     Então
    0.45
     बम
    0.44
    വൃത്തി
    0.44
     "//
    0.44
    POSITIVE LOGITS
    list
    0.55
    and
    0.52
    vers
    0.52
    version
    0.51
    islation
    0.50
    vs
    0.50
    ons
    0.50
    vr
    0.50
    mil
    0.49
    card
    0.47
    Activations Density 0.001%

    No Known Activations