© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9897
    Prev
    Next
    INDEX
    Explanations

    reporting attributed statements or contrasts

    np_acts-logits-general · gemini-2.5-flash-lite

    argue that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reportedly
    0.63
     allegedly
    0.54
     নাকি
    0.50
     ఉందని
    0.50
     있다고
    0.49
     “‘
    0.48
     “…
    0.45
     údaj
    0.45
     据
    0.44
     "...
    0.43
    POSITIVE LOGITS
    雖然
    0.61
     although
    0.54
    虽然
    0.54
    ječ
    0.51
     embora
    0.49
    although
    0.49
     हालांकि
    0.48
     இருப்பினும்
    0.47
     сожалению
    0.46
     যদিও
    0.45
    Activations Density 0.086%

    No Known Activations