© 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. 184434
    Prev
    Next
    INDEX
    Explanations

    parentheticals followed by list items

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

    Okay, then

    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
    getCQL
    0.50
    ༦
    0.50
    שי
    0.47
    χι
    0.46
     বিরাজ
    0.46
    ջ
    0.45
     Dispon
    0.44
     Buf
    0.43
     Tiene
    0.43
     Actualmente
    0.42
    POSITIVE LOGITS
     $^{\
    0.50
     interviews
    0.44
     ambiguity
    0.42
    ere
    0.42
    hart
    0.42
    alese
    0.41
     بيد
    0.41
    n
    0.41
    abag
    0.40
    oll
    0.40
    Activations Density 0.001%

    No Known Activations