© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137822
    Prev
    Next
    INDEX
    Explanations

    . , : ?

    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_262k_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
     legitimately
    0.45
    slidesPerView
    0.45
     reduct
    0.44
     extremity
    0.43
     doorways
    0.43
    }%
    0.42
     Vacc
    0.42
    훨
    0.42
     perceive
    0.41
     unheard
    0.41
    POSITIVE LOGITS
    滋
    0.45
    inah
    0.43
    andae
    0.42
    iapan
    0.42
    スタル
    0.42
    农业
    0.42
     każde
    0.42
    ÖR
    0.41
    CHEC
    0.41
    枓
    0.41
    Activations Density 0.006%

    No Known Activations