© 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. 31-GEMMASCOPE-2-RES-262K
    7. 10240
    Prev
    Next
    INDEX
    Explanations

    ease aches and pains

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

    everyday actions and outcomes

    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_31_width_262k_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
    4
    0.36
    :
    0.35
    5
    0.34
    3
    0.33
     désormais
    0.33
     ఇటీ
    0.32
     Thursday
    0.32
     übrigens
    0.30
    2
    0.30
     Enhanced
    0.30
    POSITIVE LOGITS
    جميع
    0.35
     ಆದ್ದರಿಂದ
    0.35
     त्यांना
    0.34
    だから
    0.34
     دیگه
    0.34
     mingling
    0.34
    they
    0.34
     wodurch
    0.33
    geme
    0.33
     mereka
    0.32
    Activations Density 0.013%

    No Known Activations