© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 35964
    Prev
    Next
    INDEX
    Explanations

    London locations like Merton SW and Castle SE

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

    food or country details

    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
     toplam
    0.56
     πολλά
    0.53
     très
    0.51
     più
    0.50
     Rv
    0.50
    ὖ
    0.50
     sesión
    0.49
     surname
    0.48
     varietà
    0.47
     шкі
    0.47
    POSITIVE LOGITS
    为大家
    0.53
    *
    0.51
    Vive
    0.50
    o
    0.49
    Dice
    0.48
    gatsby
    0.46
    ता
    0.45
    With
    0.45
    되어
    0.45
    Those
    0.44
    Activations Density 0.000%

    No Known Activations