© 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. 33045
    Prev
    Next
    INDEX
    Explanations

    Listen to

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

    protection and emotional states

    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
    Bottom
    0.49
    Umb
    0.48
    Paula
    0.44
    阂
    0.44
    ilg
    0.43
    냐면
    0.42
    Michelle
    0.42
    umn
    0.41
    沟通
    0.41
    Arms
    0.41
    POSITIVE LOGITS
     iee
    0.49
     PROTECTION
    0.46
     SAFETY
    0.44
    ０
    0.44
     afraid
    0.44
    ЕТ
    0.44
     certi
    0.43
    𝟎
    0.43
     OFDM
    0.43
    ５
    0.43
    Activations Density 0.000%

    No Known Activations