© 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. 159649
    Prev
    Next
    INDEX
    Explanations

    historically authentic

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

    explaining breakdowns and specializations

    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
     proporcion
    0.48
     nahezu
    0.46
    رام
    0.45
     sociocultural
    0.44
    ﭼ
    0.43
     banyak
    0.43
    齟
    0.43
    イス
    0.42
     جان
    0.42
     პარ
    0.42
    POSITIVE LOGITS
     unopened
    0.43
     আমায়
    0.42
    epsilon
    0.41
    есть
    0.40
     frosted
    0.40
    %%\
    0.40
     হইলেই
    0.39
     earrings
    0.39
     тог
    0.39
    vious
    0.39
    Activations Density 0.001%

    No Known Activations