© 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. 134684
    Prev
    Next
    INDEX
    Explanations

    dumpster size

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

    examples like and

    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
     कोऑ
    0.50
     soltanto
    0.48
     zadr
    0.44
    retain
    0.44
     법
    0.44
     earum
    0.44
    کن
    0.42
     retain
    0.41
     potrebbero
    0.41
    definite
    0.40
    POSITIVE LOGITS
     transgress
    0.44
     Lep
    0.44
     essence
    0.43
     infrastructural
    0.42
    Lep
    0.42
     तेरा
    0.41
    शल
    0.40
     veggies
    0.40
    ิ
    0.40
    เทศ
    0.40
    Activations Density 0.003%

    No Known Activations