© 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. 86396
    Prev
    Next
    INDEX
    Explanations

    press release, superior pricing, usage rights

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

    possession played, single words, Real Estate, close systems, companies tax returns

    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
     করিল
    0.51
    <0x99>
    0.49
    andı
    0.49
    ಾಟ
    0.48
     ليه
    0.48
    स्थिति
    0.47
    altered
    0.47
    dır
    0.46
     அல்லாஹ்வின்
    0.46
    })+\
    0.46
    POSITIVE LOGITS
     Aust
    0.47
    8
    0.47
    '
    0.45
     functors
    0.44
    Aust
    0.44
    kent
    0.44
     photons
    0.43
    DOF
    0.43
    6
    0.43
     Miner
    0.42
    Activations Density 0.000%

    No Known Activations