© 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. 15-GEMMASCOPE-2-RES-16K
    7. 2210
    Prev
    Next
    INDEX
    Explanations

    changes made

    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_15_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
     poisoned
    1.29
    rind
    1.17
    Tenn
    1.14
     getToken
    1.12
    垄
    1.12
    erapia
    1.09
    Pent
    1.07
     pent
    1.07
    答え
    1.06
     teaming
    1.06
    POSITIVE LOGITS
     apport
    1.73
    幅度
    1.69
    áveis
    1.61
     minor
    1.57
     внесен
    1.52
     відбу
    1.52
     جذر
    1.51
     الجذر
    1.50
     возмо
    1.50
    꾀
    1.48
    Activations Density 0.342%

    No Known Activations