© 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. 4400
    Prev
    Next
    INDEX
    Explanations

    as expected

    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
    Neces
    1.31
     compréhension
    1.21
     revenus
    1.20
    contacto
    1.15
    .'%
    1.15
    ítez
    1.12
    aufgaben
    1.10
     veya
    1.09
    attenzione
    1.08
    右手
    1.06
    POSITIVE LOGITS
     threw
    2.10
    撤
    2.08
     throw
    2.03
     Increment
    1.99
     injected
    1.96
     Nore
    1.96
     fired
    1.95
     repeal
    1.93
     Supp
    1.91
     repro
    1.90
    Activations Density 0.000%

    No Known Activations