© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13389
    Prev
    Next
    INDEX
    Explanations

    joining

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     कहला
    0.52
    ullahi
    0.50
    اوم
    0.49
    }|=
    0.47
    stehung
    0.46
     }}=
    0.46
     যাক
    0.46
    }=[
    0.46
    }}=
    0.45
     }=
    0.45
    POSITIVE LOGITS
     coupled
    4.19
     combined
    3.84
    combined
    3.50
    coupled
    3.48
     Coupled
    3.45
     paired
    3.42
     Combined
    3.16
    Combined
    3.09
     accompanied
    3.00
     همراه
    2.95
    Activations Density 0.465%

    No Known Activations