© 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. 3274
    Prev
    Next
    INDEX
    Explanations

    use of 'not' for validation

    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
     संतुल
    1.77
     божомолдору
    1.67
    谲
    1.67
    .-\
    1.66
    htë
    1.65
    ጇ
    1.65
    簱
    1.65
    ጺ
    1.61
     hiển
    1.60
     божомолу
    1.59
    POSITIVE LOGITS
     amazing
    1.33
     huge
    1.29
     fantastic
    1.26
     Charles
    1.24
     incredible
    1.23
     excellent
    1.20
     grande
    1.19
    en
    1.18
     incredibly
    1.17
     enormous
    1.17
    Activations Density 0.051%

    No Known Activations