© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24085
    Prev
    Next
    INDEX
    Explanations

    purchasing Treasury Securities displacement address

    np_acts-logits-general · gemini-2.5-flash-lite

    refusal phrases "**absolutely cannot**"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ichtet
    0.46
     ზ
    0.45
    е
    0.43
    Accueil
    0.42
    Deux
    0.42
    Ar
    0.41
    ich
    0.40
    겠지만
    0.40
    대
    0.40
    We
    0.40
    POSITIVE LOGITS
     berupa
    0.40
    rió
    0.37
     veranda
    0.37
     ulterior
    0.36
     Nutr
    0.35
     culp
    0.35
     intervención
    0.35
     GridPane
    0.35
     bukti
    0.35
     láp
    0.35
    Activations Density 0.001%

    No Known Activations