© 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. 189875
    Prev
    Next
    INDEX
    Explanations

    ARRL

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

    explaining how to build or replicate

    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
     disgraced
    0.44
     छोड़
    0.43
     خالی
    0.43
     ruined
    0.42
     تباہ
    0.42
    }"/>
    0.41
     директора
    0.40
     प्रीवियस
    0.40
     huy
    0.39
     buen
    0.39
    POSITIVE LOGITS
     ቦ
    0.48
    맘
    0.46
    𝒐
    0.46
    ાર્
    0.45
    fence
    0.44
    OK
    0.44
     BorderLayout
    0.43
     project
    0.43
    ्लाई
    0.43
     VERSION
    0.42
    Activations Density 0.000%

    No Known Activations