© 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. 27328
    Prev
    Next
    INDEX
    Explanations

    specific feature or brand evolution

    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
     pourcentage
    0.48
     Emotional
    0.47
     большие
    0.44
     percentuale
    0.43
    骶
    0.43
     بچہ
    0.42
     эмоциона
    0.42
     Tako
    0.42
     partecipazione
    0.41
     తల్లి
    0.41
    POSITIVE LOGITS
    یکیشن
    0.45
    kW
    0.43
     diners
    0.42
    Joe
    0.41
    ny
    0.40
    z
    0.40
     operating
    0.38
    Μ
    0.38
    ulner
    0.37
    wurf
    0.37
    Activations Density 0.033%

    No Known Activations