© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3295
    Prev
    Next
    INDEX
    Explanations

    security and authentication

    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
    odată
    1.38
    を経て
    1.30
     soon
    1.25
    elapsed
    1.24
    渴望
    1.23
     begin
    1.22
    瘾
    1.21
    倦
    1.18
    饥
    1.18
    ilmente
    1.17
    POSITIVE LOGITS
     mooring
    1.62
     beneficiary
    1.47
     céd
    1.47
     removeItem
    1.44
     reconfiguration
    1.43
     redirection
    1.42
    camera
    1.41
     unobstructed
    1.40
    firing
    1.40
     taps
    1.40
    Activations Density 0.008%

    No Known Activations