© 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. 156583
    Prev
    Next
    INDEX
    Explanations

    social channel, larger frames, within our

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

    health and indicators

    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
    Walter
    0.42
    steel
    0.40
     ਸਿੰ
    0.39
    цыяна
    0.39
    Eric
    0.38
    S
    0.38
    positioned
    0.38
    ﺎ
    0.38
     বিদেশে
    0.37
    foreign
    0.37
    POSITIVE LOGITS
     melding
    0.46
    omponent
    0.45
     alpin
    0.44
     slits
    0.43
     ultrap
    0.43
     nanoparticle
    0.43
    čar
    0.43
     iteration
    0.42
     pseudos
    0.42
     ramai
    0.42
    Activations Density 0.000%

    No Known Activations