© 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. 16106
    Prev
    Next
    INDEX
    Explanations

    exemplary readings

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

    the suspect left behind

    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
     ഒഴിവാ
    0.38
    falt
    0.37
    with
    0.34
     عايزين
    0.34
    tonne
    0.34
     плюс
    0.33
    䆔
    0.33
     มี
    0.33
    furn
    0.32
     არს
    0.32
    POSITIVE LOGITS
     erythro
    0.39
     priestly
    0.37
    ایا
    0.37
     clergy
    0.35
    ഹ്
    0.35
    ья
    0.32
     médical
    0.32
    میان
    0.32
    わせて
    0.32
     goddess
    0.32
    Activations Density 0.000%

    No Known Activations