© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10615
    Prev
    Next
    INDEX
    Explanations

    news datelines location information

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

    crisis hotlines and resources

    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_40_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
    öff
    0.44
    })]
    0.41
    شرين
    0.41
    ቝ
    0.41
    いただいた
    0.40
    📬
    0.40
    णाऱ्या
    0.39
    üren
    0.39
    ဦ
    0.39
    の一つ
    0.39
    POSITIVE LOGITS
    ﾓ
    0.47
     Ingles
    0.43
     several
    0.41
     несколько
    0.40
     plusieurs
    0.39
     freeze
    0.39
     EV
    0.39
     похоже
    0.38
     евро
    0.38
    0.38
    Activations Density 0.023%

    No Known Activations