© 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. 47337
    Prev
    Next
    INDEX
    Explanations

    conditional phrases with too

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

    formulating a response

    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
     nondestructive
    0.45
     destructive
    0.44
     flooded
    0.43
     நன்றி
    0.42
    Klas
    0.40
    亚
    0.40
    챕
    0.40
     ઘટના
    0.39
    <0xA5>
    0.39
    펴
    0.39
    POSITIVE LOGITS
     also
    0.47
     también
    0.47
    也會
    0.47
     można
    0.46
     можна
    0.43
     også
    0.42
    也要
    0.42
    或者是
    0.42
     cũng
    0.41
     juga
    0.41
    Activations Density 0.000%

    No Known Activations