© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11831
    Prev
    Next
    INDEX
    Explanations

    padding colon

    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_7_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
    ி
    2.50
    нув
    2.36
    }$.
    2.25
    হেতু
    2.24
    T
    2.24
     compet
    2.16
    할
    2.16
    multline
    2.12
    ించి
    2.09
    ා
    2.08
    POSITIVE LOGITS
    此之外
    2.77
    BeginInit
    2.77
    𝘻
    2.74
    hia
    2.59
    다면
    2.57
    larda
    2.56
    다고
    2.49
     चलिए
    2.42
     thisComponent
    2.40
    lož
    2.40
    Activations Density 0.011%

    No Known Activations