© 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. 191139
    Prev
    Next
    INDEX
    Explanations

    ending sentences with apple

    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
     sulfonic
    0.42
     Gin
    0.38
     {\
    0.36
    বি
    0.35
     Mallory
    0.35
    Gin
    0.35
     Amy
    0.34
    oxane
    0.33
     lefty
    0.33
     Norden
    0.33
    POSITIVE LOGITS
    yata
    0.41
    embro
    0.40
    )((
    0.40
    𝗧
    0.38
     ಅರ್ಥ
    0.38
    ERRE
    0.38
    ЕМ
    0.37
    Assembl
    0.37
    intention
    0.37
     பொருள்
    0.36
    Activations Density 0.006%

    No Known Activations