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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17807
    Prev
    Next
    INDEX
    Explanations

    AIC, IC, ric, fic, Alic parts

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

    flick or IC followed by specific words

    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_53_width_65k_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
    撥
    0.42
    sächlich
    0.40
    piry
    0.39
     opr
    0.38
    圏
    0.38
    ும்போது
    0.38
     hank
    0.37
     sejahtera
    0.36
     phosphoric
    0.36
    itamos
    0.36
    POSITIVE LOGITS
    렴
    0.41
    HLER
    0.40
    ͹
    0.39
    ungunya
    0.38
    堭
    0.38
     السابق
    0.38
    finally
    0.37
     உங்க
    0.37
    cadilly
    0.37
    では
    0.36
    Activations Density 0.083%

    No Known Activations