© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4055
    Prev
    Next
    INDEX
    Explanations

    service, programs, theme

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    3.14
    .].
    2.96
    。
    2.95
    .]
    2.90
    .).
    2.85
    。.
    2.76
    ].
    2.74
    ®.
    2.61
    __.
    2.58
    .").
    2.57
    POSITIVE LOGITS
    ุ้น
    1.03
     πολ
    0.99
     يك
    0.99
    τρο
    0.97
     whilst
    0.95
    ネタ
    0.94
     helps
    0.92
    duit
    0.91
    ώνει
    0.91
     waxay
    0.91
    Activations Density 0.344%

    No Known Activations