© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14801
    Prev
    Next
    INDEX
    Explanations

    your vault structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ładow
    1.31
    ahon
    1.17
    ′-
    1.16
     Terrain
    1.16
     ஹை
    1.14
    ulte
    1.14
    hares
    1.12
     hash
    1.12
    แต่ละ
    1.12
    eneuve
    1.11
    POSITIVE LOGITS
    ى
    1.35
    ively
    1.22
     knowing
    1.21
     المدرسة
    1.18
     Marlon
    1.17
     kriminal
    1.12
     kiel
    1.10
     그
    1.07
     profe
    1.07
     pengetahuan
    1.06
    Activations Density 0.000%

    No Known Activations