© 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. 28440
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    attraction, desirable, strengths

    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
     millones
    0.45
    㖦
    0.44
    ঞ্চলিক
    0.42
    গুরু
    0.42
     decenas
    0.42
    INDIA
    0.41
     indiquer
    0.41
     disminución
    0.41
     controllare
    0.41
     forskjellige
    0.41
    POSITIVE LOGITS
    ana
    0.52
    的东西
    0.48
     यामध्ये
    0.45
    嫦
    0.45
    ahuasca
    0.45
    pokemon
    0.44
    看完
    0.44
    biology
    0.44
    公元
    0.44
    onge
    0.43
    Activations Density 0.000%

    No Known Activations