© 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. 166021
    Prev
    Next
    INDEX
    Explanations

    method is being

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

    buckle up, requires commitment

    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
    ր
    0.47
     massive
    0.43
     lurking
    0.42
     Staff
    0.42
     quell
    0.42
     SS
    0.42
    could
    0.41
    滓
    0.41
    II
    0.41
     (
    0.40
    POSITIVE LOGITS
     მნიშვნელ
    0.55
     সম্মান
    0.52
     保存
    0.52
     δημ
    0.51
    imageNamed
    0.51
     گاه
    0.50
     প
    0.50
    цька
    0.49
     فایل
    0.48
     skapa
    0.48
    Activations Density 0.000%

    No Known Activations