© 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. 3679
    Prev
    Next
    INDEX
    Explanations

    irresponsible

    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
    <bos>
    3.15
    ್ಯ
    2.25
    tenham
    2.23
    UNG
    2.18
    િત
    2.14
    ted
    2.09
    झे
    2.05
    ming
    2.01
    talent
    1.98
     fossa
    1.97
    POSITIVE LOGITS
     refusal
    2.81
    申し上げ
    2.78
    e
    2.60
    ழ்பெற்ற
    2.54
     отказыва
    2.48
    िली
    2.43
    े
    2.42
    ivore
    2.41
     catég
    2.40
    efeller
    2.36
    Activations Density 0.086%

    No Known Activations