© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 161
    Prev
    Next
    INDEX
    Explanations

    effects around

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

    If, what, then, into

    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_16k_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
    NSDictionary
    0.24
    dV
    0.23
    }=
    0.23
    ]=
    0.22
     indexPath
    0.22
     khen
    0.22
    km
    0.22
    NotBlank
    0.22
    ='"+
    0.22
    elem
    0.21
    POSITIVE LOGITS
    <unused2123>
    0.33
    <unused2121>
    0.31
    <unused2171>
    0.30
     Якщо
    0.29
    <unused2176>
    0.29
    <unused2148>
    0.29
    <unused2186>
    0.28
    Якщо
    0.28
     Antônio
    0.28
    ߋ
    0.28
    Activations Density 0.304%

    No Known Activations