© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2290
    Prev
    Next
    INDEX
    Explanations

    Important Note

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    er
    2.59
    い
    1.68
     fairly
    1.67
    り
    1.61
    ت
    1.59
    у
    1.57
    ו
    1.56
    ર
    1.53
    oretically
    1.51
    pounds
    1.51
    POSITIVE LOGITS
     bilayers
    1.43
     doom
    1.29
    служ
    1.25
     clauses
    1.23
     cuerpos
    1.22
    RAchievement
    1.21
    érance
    1.20
     Hinweise
    1.20
     أن
    1.19
    ACAO
    1.18
    Activations Density 0.081%

    No Known Activations