© 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
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 1823
    Prev
    Next
    INDEX
    Explanations

    circle is, solve real

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     nails
    1.06
     nets
    1.06
    ungannya
    0.99
    N
    0.97
     Net
    0.95
     (£
    0.94
     Nails
    0.94
    コツ
    0.94
     TN
    0.94
     Ness
    0.92
    POSITIVE LOGITS
    avic
    1.23
     fizik
    1.19
    }°
    1.18
     makeSound
    1.16
     Chalmers
    1.16
    чай
    1.14
    Diffuse
    1.13
     izol
    1.12
    ADI
    1.09
    PUR
    1.09
    Activations Density 0.294%

    No Known Activations