© 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. 4239
    Prev
    Next
    INDEX
    Explanations

    keep your things

    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
    <0x0D>
    0.48
    0.47
    ف
    0.47
     '['
    0.46
    ه
    0.46
    ك
    0.45
                        
    0.45
                 
    0.44
    0.44
     trás
    0.44
    POSITIVE LOGITS
     keep
    0.92
    Keep
    0.90
    keep
    0.90
    keeps
    0.75
     Keep
    0.74
    KEEP
    0.70
    stay
    0.65
     on
    0.64
    kept
    0.63
     KEEP
    0.63
    Activations Density 0.047%

    No Known Activations