© 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. 192154
    Prev
    Next
    INDEX
    Explanations

    Mercury Glass, safe handling, Buyer

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

    changing states or conditions

    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
    朤
    0.48
     unlawfully
    0.47
    大约
    0.46
     supergiants
    0.46
     тысячи
    0.46
     न्याय
    0.45
    חק
    0.45
    rimin
    0.44
    ర్థ
    0.44
     价
    0.43
    POSITIVE LOGITS
    ører
    0.47
    áme
    0.45
    er
    0.44
    ੇ
    0.43
    azione
    0.42
     vendredi
    0.42
     vous
    0.42
    ুণ
    0.42
    ati
    0.41
    elijk
    0.41
    Activations Density 0.000%

    No Known Activations