© 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. 8153
    Prev
    Next
    INDEX
    Explanations

    list separators and categories

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

    get, verify, or new

    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
     eaten
    0.42
                     
    0.40
     Wain
    0.40
     nltk
    0.40
     Stéph
    0.38
     rubbish
    0.38
     rumble
    0.38
    |)
    0.38
     edible
    0.38
    ...........
    0.38
    POSITIVE LOGITS
    get
    0.49
    анали
    0.45
     निराशा
    0.44
    գ
    0.44
    ה
    0.43
     sababu
    0.42
    መሪያ
    0.42
    normalization
    0.41
    ORES
    0.41
    <unused721>
    0.40
    Activations Density 0.001%

    No Known Activations