© 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-262K
    7. 170430
    Prev
    Next
    INDEX
    Explanations

    **:** delimiting lists or code

    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
     ಅಂಶ
    0.49
    </bbox>
    0.48
    ধারণ
    0.47
    𝗿
    0.47
    AnimationStyle
    0.47
    ዔ
    0.46
    แนว
    0.46
     আকারে
    0.46
     ایڈ
    0.46
     대응
    0.46
    POSITIVE LOGITS
     drain
    0.46
    öz
    0.44
    y
    0.43
     conm
    0.42
     subsequently
    0.41
     bumble
    0.41
    at
    0.41
     disruptive
    0.41
    !
    0.40
     comercial
    0.40
    Activations Density 0.010%

    No Known Activations