© 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. 11758
    Prev
    Next
    INDEX
    Explanations

    leaving or ending relationships

    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
    ोब
    1.49
    ೂರ್ವ
    1.32
    たん
    1.28
    𝚞
    1.27
    꺅
    1.23
     तिथ
    1.21
    しない
    1.20
     mitt
    1.20
    guardo
    1.20
    fti
    1.19
    POSITIVE LOGITS
    狽
    1.77
    ům
    1.64
    entesque
    1.53
     Richt
    1.53
    ędzie
    1.53
     znaleźć
    1.50
    امر
    1.49
    ıza
    1.48
     Assurance
    1.47
    JUN
    1.46
    Activations Density 0.053%

    No Known Activations