© 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. 32223
    Prev
    Next
    INDEX
    Explanations

    no runtime overhead

    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
    ținut
    0.47
     Taş
    0.46
    O
    0.45
    ছার
    0.44
    zac
    0.44
    slut
    0.44
    nav
    0.43
     saisir
    0.42
     It
    0.41
     Camacho
    0.41
    POSITIVE LOGITS
    ли
    0.47
    约为
    0.45
     թ
    0.44
    hehi
    0.44
     висо
    0.44
    较高
    0.44
     concepts
    0.43
    向け
    0.43
     amplitudes
    0.42
     اہم
    0.41
    Activations Density 0.001%

    No Known Activations