© 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. 208971
    Prev
    Next
    INDEX
    Explanations

    reversed or opposite

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

    closing or continuing instructions

    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
     a
    0.58
     the
    0.49
     Bonnie
    0.48
     those
    0.45
     care
    0.45
     Richie
    0.44
    湫
    0.44
    P
    0.44
    淑
    0.43
     Gub
    0.43
    POSITIVE LOGITS
    nimmt
    0.52
     erfolgt
    0.49
    جين
    0.48
    ឮ
    0.47
    approval
    0.44
    gekehrt
    0.44
     அவசியம்
    0.44
     Hinweis
    0.43
    functioning
    0.43
    ្ស
    0.43
    Activations Density 0.001%

    No Known Activations