© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5283
    Prev
    Next
    INDEX
    Explanations

    low rumble or hum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    nd
    1.00
    NN
    0.95
     share
    0.91
     Transformers
    0.88
     propensity
    0.88
    να
    0.87
     Manifest
    0.87
     *
    0.86
     figured
    0.85
     merchandise
    0.85
    POSITIVE LOGITS
    }}_{\
    1.44
    刹
    1.42
    opacity
    1.36
    靘
    1.36
    }}_{
    1.35
    }_{+
    1.34
    }}_
    1.34
     transparen
    1.32
     lym
    1.31
    apaccay
    1.31
    Activations Density 0.046%

    No Known Activations