© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6666
    Prev
    Next
    INDEX
    Explanations

    saying or telling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     -
    0.59
     Appel
    0.53
    ب
    0.51
     pyl
    0.49
     glimpses
    0.47
     Haber
    0.47
     (
    0.46
    rieben
    0.46
     UPSC
    0.45
     Ade
    0.45
    POSITIVE LOGITS
     aloud
    0.76
    实话
    0.68
     loudly
    0.66
    loud
    0.63
     louder
    0.58
    about
    0.56
    áról
    0.56
     عنه
    0.55
     apie
    0.54
    說
    0.54
    Activations Density 0.144%

    No Known Activations