© 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. 130945
    Prev
    Next
    INDEX
    Explanations

    pm time stamps in blog posts

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

    cause hyp; Best Coffee; Amazon controls

    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
    en
    0.48
     vesting
    0.46
    qh
    0.45
    Paw
    0.45
    q
    0.43
     inher
    0.41
     Paw
    0.40
    一度
    0.40
    侔
    0.40
    Ath
    0.40
    POSITIVE LOGITS
     പൂര്‍
    0.52
    preneur
    0.50
     investimento
    0.49
     კონ
    0.48
     ორ
    0.47
    зумі
    0.47
     empres
    0.46
    アント
    0.46
    υσ
    0.46
     مردم
    0.46
    Activations Density 0.001%

    No Known Activations