© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4185
    Prev
    Next
    INDEX
    Explanations

    names after "named"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
     Hilary
    2.23
     rsp
    2.22
     寝
    2.22
     Oprah
    2.21
     unver
    2.21
     Prius
    2.14
     destru
    2.13
     Presiden
    2.13
     Pudding
    2.13
     Bled
    2.12
    POSITIVE LOGITS
    apun
    0.64
    en
    0.54
    y
    0.46
     الثانو
    0.45
    Y
    0.44
     принадле
    0.43
    el
    0.42
    ye
    0.41
    work
    0.40
    al
    0.38
    Activations Density 0.122%

    No Known Activations