© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5864
    Prev
    Next
    INDEX
    Explanations

    stand up, back away, lodge itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ור
    1.28
    া
    1.28
    要想
    1.23
    ли
    1.21
    ional
    1.21
    ום
    1.20
    ड्ड
    1.20
    ጨማሪ
    1.17
    그래서
    1.16
    ☐
    1.12
    POSITIVE LOGITS
     the
    1.55
     it
    1.51
     a
    1.37
    AR
    1.36
     தனது
    1.36
    ТИ
    1.34
     wyłącznie
    1.33
    LE
    1.32
    CUSSION
    1.29
    HE
    1.28
    Activations Density 0.080%

    No Known Activations