© 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-65K
    7. 52398
    Prev
    Next
    INDEX
    Explanations

    lists, numbers, 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_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
     كال
    0.46
     qualitatively
    0.44
    ມັນ
    0.44
    రం
    0.44
     кварти
    0.43
    их
    0.43
    ريض
    0.42
    !</
    0.42
    ثير
    0.41
    कहीं
    0.41
    POSITIVE LOGITS
    ilina
    0.48
     行っ
    0.48
     जीवों
    0.45
     vrchol
    0.45
    TRAS
    0.44
    omorphism
    0.43
     selectors
    0.43
     personalisation
    0.43
     etapas
    0.42
    メリカ
    0.42
    Activations Density 0.001%

    No Known Activations