© 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. 40-GEMMASCOPE-2-RES-262K
    7. 204428
    Prev
    Next
    INDEX
    Explanations

    song of freedom

    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_40_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
     riding
    0.37
    。
    0.37
    ાર
    0.37
    IBM
    0.36
     finales
    0.36
    Fitting
    0.35
    CCIÓN
    0.35
     tiring
    0.34
     medir
    0.34
    脉
    0.34
    POSITIVE LOGITS
    DbType
    0.46
     Edwards
    0.41
    liques
    0.41
     Dant
    0.40
    dan
    0.39
     Dan
    0.38
    relationships
    0.38
    opol
    0.38
    更加
    0.37
     conceded
    0.37
    Activations Density 0.001%

    No Known Activations