© 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. 3627
    Prev
    Next
    INDEX
    Explanations

    remove or use

    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
     Young
    0.75
    Young
    0.70
     young
    0.67
     céré
    0.66
     Adolescent
    0.65
    otemporal
    0.63
    rod
    0.59
    蓉
    0.59
    ʿ
    0.58
    youth
    0.57
    POSITIVE LOGITS
     declaration
    2.35
    declaration
    2.24
     Declar
    2.24
    Declaration
    2.24
     Declaration
    2.23
     declarations
    2.23
     Declare
    2.21
    declared
    2.18
     declaring
    2.17
    DECL
    2.14
    Activations Density 0.014%

    No Known Activations