© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 5789
    Prev
    Next
    INDEX
    Explanations

    city | twitter | fat

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

    key-value pairs and definitions

    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
    }^{+}$.
    0.38
    ங்களுடன்
    0.37
     कोणताही
    0.36
    !”.
    0.35
    கோ
    0.34
    !”,
    0.34
    <unused40>
    0.33
    鈞
    0.32
     இவ்வாறு
    0.32
     থাকিলেও
    0.32
    POSITIVE LOGITS
     =
    0.49
    )
    0.40
     sidebar
    0.37
    ,
    0.36
     -->
    0.35
     aka
    0.35
     -
    0.35
    に関しては
    0.35
    :
    0.34
    គឺ
    0.33
    Activations Density 0.026%

    No Known Activations