© 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. 35323
    Prev
    Next
    INDEX
    Explanations

    occurrence and location

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

    then came / will inevitably / divisible by

    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
     Undo
    0.46
    みが
    0.45
     पुष्टि
    0.45
     základě
    0.44
     तबीयत
    0.43
    炁
    0.42
    ]";
    0.41
     Question
    0.41
    <0xDE>
    0.40
     Tsai
    0.40
    POSITIVE LOGITS
    gaver
    0.44
     duplex
    0.43
     hidrául
    0.42
     contratar
    0.39
    IVACON
    0.39
     centres
    0.39
     chasse
    0.39
    valuer
    0.38
    aronne
    0.38
     veines
    0.38
    Activations Density 0.001%

    No Known Activations