© 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. 202877
    Prev
    Next
    INDEX
    Explanations

    phase two:

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

    consistently delivering/meeting

    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
     החד
    0.47
    '},
    0.46
     חד
    0.46
    ដំណ
    0.45
     Enquanto
    0.45
    Tags
    0.44
     })
    0.44
    новый
    0.43
    '})
    0.43
     estando
    0.43
    POSITIVE LOGITS
    กรม
    0.49
     Z
    0.44
     OST
    0.44
    詣
    0.43
     Episc
    0.43
    酞
    0.43
    aniti
    0.43
    ს
    0.43
    лів
    0.42
    ৤
    0.42
    Activations Density 0.001%

    No Known Activations