© 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. 179629
    Prev
    Next
    INDEX
    Explanations

    access to

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

    preventing her from | without death

    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
     ਵੱ
    0.43
    upati
    0.41
     ਮੁ
    0.40
    把我
    0.40
     ਬ
    0.40
    ਿੰ
    0.40
     కొంత
    0.39
    Quanto
    0.39
    ።
    0.39
    redit
    0.38
    POSITIVE LOGITS
     AGENCY
    0.52
     với
    0.47
     లేదా
    0.47
     Agency
    0.46
     hoặc
    0.46
     đảm
    0.46
     Deutsches
    0.44
    ımız
    0.43
     estábamos
    0.43
     şeklinde
    0.43
    Activations Density 0.002%

    No Known Activations