© 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. 233184
    Prev
    Next
    INDEX
    Explanations

    words 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_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
     this
    0.51
     możesz
    0.51
     otra
    0.49
     poursuit
    0.48
     outra
    0.48
    W
    0.47
    aire
    0.46
     diga
    0.46
    看一下
    0.45
     rozum
    0.45
    POSITIVE LOGITS
    దా
    0.50
     Bö
    0.46
    ành
    0.46
    」。
    0.44
    }^{(\
    0.44
    ۋ
    0.44
    䍩
    0.43
    ிஸ்த
    0.43
    劻
    0.43
    î
    0.42
    Activations Density 0.000%

    No Known Activations